A shield machine cutterhead center area deformation detection system and method

Abstract

The present invention belongs to the technical field of deformation detection in the center area of the cutterhead of a shield machine, and discloses a system and method for detecting deformation in the center area of the cutterhead of a shield machine. The present invention realizes intelligent deformation monitoring of the center area of the cutterhead of a shield machine by establishing a correlation model between dynamic load and static deformation, comprehensively evaluating the deformation in the center area of the cutterhead of a shield machine, and integrating multi-dimensional parameters such as vibration spectrum, temperature gradient, and stress distribution, and establishing a prediction algorithm in combination with material fatigue characteristics, thereby improving the deformation monitoring recognition rate and significantly improving construction safety and equipment reliability. The present invention identifies deformation areas and risk areas based on a correlation model between dynamic load and static deformation, and can accurately identify deformation areas and divide risk levels, realize early risk prediction and proactive maintenance, break through the limitations of traditional methods of only detecting deformed states, and significantly improve the foresight and reliability of cutterhead health management.

Description

Technical Field

[0001] The invention belongs to the technical field of shield machine cutter head central area deformation detection, and relates to a shield machine cutter head central area deformation detection system and method. Background Art

[0002] A shield machine is a large-scale construction machine used for tunnel construction. It consists of a shield, a cutterhead, and a cutting system. The cutterhead, located at the front end of the machine, is the key component for cutting soil. Various cutting tools are mounted in the center of the cutterhead. When the machine begins tunneling, these tools first come into contact with the ground, initially crushing the rock and soil in the center of the tunnel. Therefore, deformation in the center of the cutterhead directly affects the efficiency, stability, and safety of the machine's tunneling operation, making its monitoring and research crucial.

[0003] Existing technologies exist for detecting deformation in the center of a shield machine cutterhead. For example, the Chinese invention patent application CN115355812A, titled "A Shield Machine Cutterhead Deformation Detection Method and System," includes the following: 1. Hard strata determination: The presence of a sustained minimum spacing at a point corresponds to the highest hardness zone on the tunnel face; 2. Cutting disc anomaly identification: When the spacing exhibits periodic changes synchronized with the cutterhead speed (with a phase difference of one cycle), a cutter fault is identified. This method uses spatiotemporal data analysis to provide real-time early warning of tunnel face hardness distribution and cutter status, assisting in optimizing tunneling parameters and equipment maintenance.

[0004] In addition, a Chinese invention patent application with publication number CN113108727B is for a shield machine and a detection system for sensing deformation of the central area of the cutterhead of a shield machine, which includes real-time monitoring of the deformation of the center of the cutterhead through a telescopic component: when the cutterhead is operating normally, the oil outlets of the first and second telescopic parts are isolated from the oil overflow port, and the hydraulic oil pressure in the oil storage chamber is stable; if the central area is concave and deformed, the two telescopic parts move toward each other to connect the oil ports, and the hydraulic oil is discharged, causing a sudden drop in pressure. The pressure sensor detects the pressure change and triggers an early warning, helping operators to promptly discover and deal with deformation problems to avoid equipment damage.

[0005] Although the above two schemes have proposed some solutions for monitoring and controlling parameters in the pelletizing process, they still have certain limitations. For example, on the one hand, the existing technical solutions only rely on dynamic parameter monitoring and ignore the collaborative analysis of static structural degradation, resulting in an increase in the missed detection rate of structural damage; and no correlation model between dynamic load and static deformation has been established, so it is impossible to warn of the cumulative deformation of the steel structure, which increases the risk of sudden fracture and the detection of abnormalities is relatively delayed.

[0006] On the other hand, existing technical solutions usually only involve the identification of detectable deformation that has already occurred, lack the identification of deformation risk situations, do not monitor early risk factors such as tool wear and abnormal stress distribution, and do not combine dynamic data (such as temperature rise, vibration, etc.) to establish a risk prediction model. It is difficult to warn of potential deformation in advance, and measures can only be taken after deformation occurs, and it is impossible to prevent problems before they occur. Summary of the Invention

[0007] In view of this, in order to solve the problems raised in the above background technology, a shield machine cutterhead center area deformation detection system and method are proposed.

[0008] The purpose of the present invention can be achieved through the following technical solutions: The first aspect of the present invention provides a shield machine cutter head center area deformation detection system, including: an area division module: based on the three-dimensional structural characteristics of the target shield machine cutter head center area, a geometric grid division algorithm is used to generate an equal-density distributed monitoring area and generate a unique code, and the center point of each monitoring area is used as a monitoring point.

[0009] Static monitoring module: Utilizes a 3D laser scanning device to scan the 3D topography data of each monitoring area in real time, performs point cloud registration and comparison with the pre-stored initial 3D data, uses image processing algorithms to perform quantitative analysis of tool wear and cutterhead surface defect assessment, and further outputs a static anomaly index.

[0010] Dynamic monitoring module: Integrates infrared thermal imaging devices, vibration sensor groups and three-dimensional scanning devices to monitor the temperature rise gradient, vibration spectrum characteristics and shield machine soil discharge morphological parameters of each monitoring area in real time, and calculates the dynamic anomaly index through a multi-source data fusion model.

[0011] Anomaly identification module: Utilizes a distributed stress sensor network embedded in monitoring points in a dot matrix arrangement to obtain the stress distribution matrix in real time and perform differential calculations with the preset reference stress field matrix, dynamically correct the anomaly judgment threshold, and perform anomaly identification based on the static anomaly index and dynamic anomaly index.

[0012] Deformation positioning module: locates and outputs deformation areas and risk areas based on anomaly recognition results.

[0013] The second aspect of the present invention provides a method for detecting deformation of the central area of the cutter head of a shield machine, including: S1, area division: based on the three-dimensional structural characteristics of the central area of the cutter head of the target shield machine, a geometric grid division algorithm is used to generate monitoring areas with equal density distribution and generate unique codes, and the center point of each monitoring area is used as a monitoring point.

[0014] S2. Static monitoring: Use a 3D laser scanning device to scan the 3D topography data of each monitoring area in real time, perform point cloud registration and comparison with the pre-stored initial 3D data, use image processing algorithms to achieve quantitative analysis of tool wear and cutterhead surface defect assessment, and further output a static anomaly index.

[0015] S3. Dynamic monitoring: Integrate infrared thermal imaging devices, vibration sensor groups and soil slag image acquisition devices to collect temperature rise gradients, vibration spectrum characteristics and shield machine soil slag discharge images of each monitoring area in real time, and calculate the dynamic anomaly index through a multi-source data fusion model.

[0016] S4. Abnormal identification: A distributed stress sensor network embedded in monitoring points in a dot matrix arrangement is used to obtain the stress distribution matrix in real time and perform differential calculation with the preset reference stress field matrix. The abnormality judgment threshold is dynamically corrected, and abnormality identification is performed based on the static abnormality index and dynamic abnormality index.

[0017] S5. Deformation positioning: Locate and output the deformed area and risk area based on the abnormality recognition results.

[0018] Compared with the existing technology, the beneficial effects of the present invention are as follows: (1) The present invention establishes a correlation model between dynamic load and static deformation, comprehensively evaluates the deformation of the central area of the shield machine cutter head, and realizes intelligent deformation monitoring of the central area of the shield machine cutter head. The system integrates multi-dimensional parameters such as vibration spectrum, temperature gradient, stress distribution, etc., and establishes a prediction algorithm based on the fatigue characteristics of the material, thereby improving the deformation monitoring recognition rate and significantly improving construction safety and equipment reliability.

[0019] (2) The present invention identifies deformation areas and risk areas based on the correlation model between dynamic load and static deformation. It can accurately identify deformation areas and classify risk levels, realize early risk prediction and proactive maintenance, break through the limitation of traditional detection of only deformed states, and significantly improve the foresight and reliability of cutterhead health management.

[0020] (3) The present invention constructs a stress distribution matrix and performs differential calculations with a preset reference stress field matrix, dynamically corrects the abnormality judgment threshold, and realizes adaptive optimization of the abnormality judgment threshold, breaking through the rigid detection limitations of traditional fixed thresholds. It can accurately identify hidden structural damage under different geological conditions, and greatly reduce the risk of misjudgment while ensuring detection sensitivity. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 This is a schematic diagram of the connection of various modules of the system of the present invention.

[0023] Figure 2 Schematic diagram of the implementation of the method steps of the present invention.

[0024] Figure 3 A schematic diagram of monitoring area division corresponding to an embodiment provided by the present invention.

[0025] Reference numerals: 1 - cutterhead, 2 - monitoring area, 3 - monitoring point. DETAILED DESCRIPTION

[0026] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0027] See also Figure 1 As shown, the first aspect of the present invention provides a shield machine cutter head central area deformation detection system, including an area division module, a static monitoring module, a dynamic monitoring module, an abnormality identification module and a deformation positioning module, wherein the area division module is connected to the static monitoring module and the dynamic monitoring module respectively, the static monitoring module and the dynamic monitoring module are both connected to the abnormality identification module, and the abnormality identification module is connected to the deformation positioning module.

[0028] The area division module is used based on the three-dimensional structural characteristics of the target shield machine cutter head center area. Figure 3 As shown in the figure, a geometric grid partitioning algorithm is used to generate monitoring areas with equal density distribution and generate unique codes, and the center point of each monitoring area is used as the monitoring point.

[0029] It should be noted that, in the actual area division process, each monitoring area may or may not have tool distribution.

[0030] The static monitoring module is used to use a three-dimensional laser scanning device to scan the three-dimensional topography data of each monitoring area in real time, perform point cloud registration and comparison with the pre-stored initial three-dimensional data, use image processing algorithms to realize quantitative analysis of tool wear and assessment of cutter head surface defects, and further output a static anomaly index.

[0031] It should be explained that the three-dimensional shape data may be three-dimensional contour information.

[0032] In a preferred embodiment of the present invention, the specific analysis process of the tool wear quantitative analysis is as follows: the actual volume of each tool is obtained based on the three-dimensional morphology data of each monitoring area obtained by real-time scanning using a three-dimensional laser scanning device, and then compared with the initial volume of each tool, and combined with the wear analysis to obtain the wear index of each tool.

[0033] Preferably, the wear index analysis method is: calculating the difference between the actual volume of each tool and the initial volume, and then calculating the ratio with the initial volume to obtain the wear index of each tool.

[0034] Several wear monitoring points are evenly distributed on the surface of each tool to obtain the corresponding monitoring thickness. Then, the monitoring thickness of each tool surface corresponding to each wear monitoring point is compared and analyzed to obtain the wear heterogeneity index of each tool.

[0035] Preferably, the wear variability index analysis method is: performing difference calculation on the monitored thickness of each wear monitoring point on the surface of each tool and the corresponding initial monitoring thickness to obtain the wear thickness of each wear monitoring point on the surface of each tool, and then performing mean calculation to obtain the average wear thickness of each tool, performing ratio calculation on the wear thickness of each wear monitoring point on the surface of each tool and the corresponding average wear thickness to obtain the wear deviation of each wear monitoring point of each tool, and then performing mean calculation to obtain the wear variability index of each tool.

[0036] The wear index and wear heterogeneity index of each tool are averaged to obtain the quantitative evaluation index of wear of each tool.

[0037] Obtain the projection position of each tool on the cutter head surface, identify the one or more monitoring areas to which these projections belong, and compile a list of tools corresponding to each monitoring area.

[0038] The wear quantitative evaluation index of each tool corresponding to each monitoring area is averaged to obtain the tool wear evaluation index of each monitoring area. If there is no tool in a monitoring area, the tool wear evaluation index of the monitoring area is set to 0.

[0039] In a preferred embodiment of the present invention, the specific analysis process of the cutter disc surface defect evaluation is as follows: the three-dimensional morphological data of each monitoring area obtained in real time by a three-dimensional laser scanning device is used to determine the number of surface defects and their actual area in each monitoring area, and then compared with the preset reference defect number and reference defect area, and the mean value is calculated and analyzed to obtain the cutter disc surface defect evaluation index of each monitoring area.

[0040] For example, the surface defect type may be cracks, wear pits, deformation, peeling, etc.

[0041] Preferably, the specific analysis method of the cutter disc surface defect evaluation index of each monitoring area is as follows: the number of surface defects in each monitoring area is compared with the preset reference defect number to obtain the surface defect number abnormality of each monitoring area, and at the same time, the actual area of each defect in each monitoring area is calculated with the preset reference defect area to obtain the defect area abnormality of each monitoring area.

[0042] The surface defect quantity anomaly and defect area anomaly of each monitoring area are fused and calculated to obtain the cutter head surface defect evaluation index of each monitoring area.

[0043] It should be noted that the above data fusion calculation method can be mean, weighted sum or maximum value, and the specific method can be pre-set based on needs.

[0044] The dynamic monitoring module is used to integrate infrared thermal imaging devices, vibration sensor groups and three-dimensional scanning devices to monitor the temperature rise gradient, vibration spectrum characteristics and shield machine soil and slag discharge morphological parameters of each monitoring area in real time, and calculate the dynamic anomaly index through a multi-source data fusion model.

[0045] In a preferred embodiment of the present invention, the specific analysis method for calculating the dynamic anomaly index through the multi-source data fusion model is as follows: based on the temperature rise gradient, vibration spectrum characteristics and shield machine soil discharge morphological parameters of each monitoring area, the temperature rise anomaly index, vibration frequency anomaly index and shield machine soil discharge morphological anomaly index of each monitoring area are constructed.

[0046] It is important to explain that the analysis of the temperature rise gradient, vibration spectrum characteristics, and shield machine soil and debris discharge morphology parameters in each monitored area is primarily intended to comprehensively and accurately assess the working status of the shield machine's cutterhead center area, identify potential problems in advance, and ensure the safe and efficient operation of the shield machine. The specific reasons are as follows: 1. Temperature rise gradient: This reflects tool wear and friction. When the tool cuts the soil, frictional heat generates, causing the cutterhead's local temperature to rise. Abnormal temperature rise gradients indicate increased tool wear and cutting forces. This analysis can promptly identify tool problems, providing a basis for replacement and maintenance. It can also detect potential local cutterhead failures and assist in determining changes in geological conditions, allowing for adjustments to construction parameters.

[0047] 2. Vibration spectrum characteristics: This reflects the operating status of the cutterhead and tool. During normal operation, the vibration frequency of the cutterhead and tool is within a certain range. If the vibration spectrum characteristics are abnormal, it may be that the tool is loose, severely worn, or there is a problem with the cutterhead structure. Analyzing this parameter can promptly identify these problems, avoid equipment damage, and ensure construction safety and progress.

[0048] 3. Soil and debris discharge morphology parameters: These can be used to determine whether the tunneling process is normal. Large fluctuations in soil and debris discharge volume or abnormal particle size distribution may indicate problems with the shield machine's cutting or debris discharge processes, such as poor tool cutting performance or a clogged debris discharge system. By analyzing these parameters, timely adjustments to construction operations can be made to ensure smooth tunneling. This also helps understand ground changes and provides a reference for subsequent construction.

[0049] The abnormal indices are fused and analyzed to obtain the dynamic abnormal index of each monitoring area, wherein the temperature rise abnormal index and vibration frequency abnormal index are for the actual situation of each monitoring area, and the shield machine's soil slag discharge morphology abnormal index is for the actual situation of the entire shield machine.

[0050] Preferably, the dynamic anomaly index is analyzed by fusing the temperature rise anomaly index, the vibration frequency anomaly index and the soil slag discharge morphology anomaly index of each monitoring area to obtain the dynamic anomaly index of each monitoring area.

[0051] It should be noted that the above data fusion calculation method can be mean, weighted sum or maximum value, and the specific method can be pre-set based on needs.

[0052] In a preferred embodiment of the present invention, the specific method of constructing the temperature rise anomaly index, vibration frequency anomaly index and shield machine soil discharge morphology anomaly index of each monitoring area is as follows: the average temperature of adjacent monitoring points is calculated as the reference temperature, and then the temperature of each monitoring point is compared with the reference temperature to analyze and obtain the temperature rise anomaly index of each monitoring area.

[0053] The specific analysis method of the vibration frequency anomaly index refers to the specific analysis method of the temperature rise anomaly index.

[0054] The soil slag discharge morphological parameters of the shield machine collected by the three-dimensional scanning device are used to evaluate the soil slag discharge volume and soil slag particle size distribution during the shield machine's soil slag discharge process, and then a comparative analysis is performed to obtain the soil slag discharge morphological anomaly index of the shield machine.

[0055] In a preferred embodiment of the present invention, the specific analysis method of the evaluation corresponding to the soil slag discharge volume and soil slag particle size distribution of the shield machine soil slag discharge process is as follows: extract the shield machine soil slag discharge morphological parameters collected by the three-dimensional scanning device, extract several batches of soil slag discharge data for the soil slag discharge parameters based on unit time intervals, obtain the soil slag volume corresponding to each batch of soil slag discharge data, analyze the soil slag discharge volume of each batch in combination with the soil slag density, and perform fluctuation analysis on the soil slag discharge volume of the batch closest to the current moment and the soil slag discharge volume of other batches to obtain the soil slag discharge volume fluctuation evaluation result.

[0056] Preferably, the discharge amount of each batch of soil residue is calculated by multiplying the volume of each batch of soil residue by the corresponding soil residue density.

[0057] Preferably, the specific analysis method of the soil debris discharge fluctuation evaluation result is: based on the shield machine soil debris discharge morphological parameters provided by the three-dimensional scanning device, multiple batches of data extraction and processing are performed within a unit time interval to determine the volume of each batch of soil debris.

[0058] The actual amount of soil slag discharged in each batch is calculated by combining the volume of soil slag in each batch with the density of soil slag.

[0059] The fluctuation analysis of the soil slag discharge volume of the latest batch and the previous batches was carried out to obtain the evaluation results of the soil slag discharge fluctuation.

[0060] Preferably, the fluctuation of soil slag discharge in other batches is obtained by performing difference calculation between the soil slag discharge in other batches and the soil slag discharge in the previous batch, and then performing ratio calculation between the soil slag discharge in the latest batch at the current moment and the soil slag discharge in the previous batch, and then performing ratio calculation between the soil slag discharge in the current batch and the soil slag discharge in the previous batch.

[0061] The soil slag discharge fluctuation index is calculated by comparing the fluctuation of the current batch of soil slag discharge with the average value of the fluctuation of the soil slag discharge of other batches.

[0062] It's important to further explain that the logic behind this step is to accurately measure the stability of the shield machine's discharge by comparing the fluctuations in the current and past batches of soil and debris discharge, providing a basis for determining the equipment's operating status. The calculation begins by first finding the average fluctuation of the soil and debris discharge of each batch, representing the general level of past discharge fluctuations. The fluctuation of the current batch's soil and debris discharge is then compared to this average. The ratio directly reflects the degree of deviation between the current fluctuation and the average level. A larger ratio indicates a more abnormal current fluctuation, indicating a possible equipment problem.

[0063] The soil debris is segmented into particles based on the point cloud segmentation algorithm to obtain the volume of each soil debris particle. Based on this, an equivalent diameter analysis is performed to obtain the equivalent diameter of each soil debris particle, and then a three-dimensional particle size distribution map is constructed. The proportion of soil debris particles in the pre-set expected particle size range is obtained and a difference analysis is performed with the pre-set reference expected particle size proportion to obtain the evaluation results of soil debris particle size distribution anomalies.

[0064] It should be noted that the specific method of performing equivalent diameter analysis is: using the formula The equivalent diameter of each soil particle is obtained by analysis ,in represents the volume of each soil particle, Indicates the number of the soil particles, , Indicates the number of soil debris particles.

[0065] It should be explained that the construction principle of the above formula is: based on the sphere volume formula, for a standard sphere, its volume formula is ,in is the volume of the sphere, is the radius of the sphere. ,Will Substituting into the volume formula we get , and then transformed to obtain the equivalent diameter analysis formula.

[0066] It's important to note that the above formula is used for this purpose: in shield machine debris analysis, debris particles are often irregular in shape, making it difficult to accurately describe their size using conventional methods. By calculating the equivalent diameter using this formula, irregular debris particles can be approximated as spheres, with a uniform diameter representing their size. This facilitates subsequent statistical analysis of debris particles, such as analyzing their particle size distribution, and can assist in determining the shield machine's cutting performance and stratum characteristics.

[0067] Preferably, the specific method of constructing the three-dimensional particle size distribution map is: comparing the equivalent diameter of each soil slag particle with the preset reference distribution diameter. Specifically, if the equivalent diameter of the soil slag particle is less than , marking it as If the equivalent diameter of the soil debris particle is greater than or equal to and less than , marking it as If the equivalent diameter of the soil debris particle is greater than or equal to and less than , marking it as If the equivalent diameter of the soil debris particle is greater than , marking it as , count the number of soil debris particles of each diameter grade, and calculate the proportion of soil debris particles of each diameter grade by comparing them with the total number of soil debris particles.

[0068] Preferably, the specific analysis method of the evaluation results of the abnormal soil debris particle size distribution is as follows: the proportion of soil debris particles of each diameter grade within the expected particle size range is summed up, the difference between the reference expected particle size proportion and the summed calculation result is calculated to obtain the expected particle size proportion failure rate, and then the ratio is calculated with the reference expected particle size proportion to obtain the soil debris particle size distribution abnormality evaluation index.

[0069] For example, if the expected particle size range is , then the diameter grade is and The soil residue particle size distribution anomaly evaluation index is obtained by summing up the proportion of soil residue particles and then performing a difference analysis with the preset reference expected particle size proportion.

[0070] The anomaly identification module is used to use a distributed stress sensor network embedded in monitoring points in a dot matrix arrangement to obtain the stress distribution matrix in real time and perform differential calculation with a preset reference stress field matrix, dynamically correct the anomaly judgment threshold, and perform anomaly identification based on static anomaly index and dynamic anomaly index.

[0071] In a preferred embodiment of the present invention, the specific method of dynamically correcting the abnormality judgment threshold is as follows: the stress distribution matrix obtained in real time is differentially calculated with the preset reference stress field matrix to obtain the stress deviation matrix of the central area of the shield machine, and then compared and analyzed with the preset reference stress deviation threshold to obtain the abnormality judgment threshold correction coefficient of each monitoring point.

[0072] Preferably, the stress distribution matrix obtained in real time is subtracted from the corresponding elements of the preset reference stress field. For example, for a two-dimensional stress distribution matrix and a reference stress field matrix, let the stress distribution matrix be , the preset reference stress field is , then the stress deviation matrix C after differential calculation is .

[0073] It should be explained that the stress distribution matrix is a two-dimensional matrix, the number of its rows and columns corresponds to the dot array of stress sensors on the shield machine. Assuming that the stress sensors are arranged in the form of m rows and n columns on the plane of the center area of the cutter head of the shield machine, the stress distribution matrix A is a Each element in the matrix ( , ) represents the stress value measured by the stress sensor located in the i-th row and j-th column.

[0074] Preferably, the analysis method of the abnormality determination threshold correction coefficient is as follows: the stress deviation of each monitoring point is calculated by ratioing the stress deviation of each monitoring point with a preset reference stress deviation threshold to obtain the abnormality determination threshold correction coefficient of each monitoring point.

[0075] The modified abnormality determination threshold of each monitoring area is constructed based on the abnormality determination threshold correction coefficient of each monitoring point and the initially set abnormality determination threshold.

[0076] Preferably, the abnormality determination threshold correction coefficient of each monitoring point is multiplied by the initially set abnormality determination threshold to obtain the corrected abnormality determination threshold of each monitoring area, wherein each monitoring point corresponds to each monitoring area.

[0077] The present invention constructs a stress distribution matrix and performs differential calculations with a preset reference stress field matrix, dynamically corrects the anomaly judgment threshold, and realizes adaptive optimization of the anomaly judgment threshold. It breaks through the rigid detection limitations of traditional fixed thresholds and can accurately identify hidden structural damage under different geological conditions, while ensuring detection sensitivity and significantly reducing the risk of misjudgment.

[0078] In a preferred embodiment of the present invention, the specific method of performing abnormality identification is as follows: a weighted sum of the static abnormality index and the dynamic abnormality index of each monitoring area is calculated to obtain a comprehensive evaluation abnormality index of each monitoring area.

[0079] It should be noted that the weightings for the static and dynamic anomaly indices are determined based on multiple factors. First, the impact on the safe operation of the cutterhead. If static factors (such as tool wear and surface defects) pose a significant threat to the long-term stability of the cutterhead, the weight of the static anomaly index can be increased. Conversely, if dynamic factors (such as temperature rise and vibration) have a more direct and significant impact, the dynamic weighting is higher. Secondly, the reliability and stability of the monitoring data are considered, and the weight of the index for accurate and reliable data is appropriately increased. The weighting is also flexibly adjusted based on the different construction stages of the shield machine and geological conditions to more accurately assess the cutterhead condition.

[0080] The comprehensive evaluation abnormality index of each monitoring area is compared with the corresponding modified abnormality judgment threshold. If the comprehensive evaluation abnormality index of a monitoring area is greater than the corresponding modified abnormality judgment threshold, it is judged that there is an abnormality in the monitoring area and it is recorded as an abnormal monitoring area. Otherwise, it is judged that there is no abnormality in the monitoring area.

[0081] It should be noted that the present invention realizes intelligent deformation monitoring of the central area of the shield machine cutter head by establishing a correlation model between dynamic load and static deformation, comprehensively evaluating the deformation of the central area of the shield machine cutter head, and integrating multi-dimensional parameters such as vibration spectrum, temperature gradient, and stress distribution. It establishes a prediction algorithm based on the fatigue characteristics of the material, thereby improving the deformation monitoring recognition rate and significantly improving construction safety and equipment reliability.

[0082] The deformation positioning module is used to locate and output deformation areas and risk areas.

[0083] In a preferred embodiment of the present invention, the specific method of locating and outputting deformation areas and risk areas is as follows: the comprehensive abnormality index of each abnormal monitoring area is arranged in descending order, and they are classified into deformation areas and risk areas according to the risk index, and the corresponding area numbers are output.

[0084] For example, it is assumed that there are five abnormal monitoring areas in the center area of the shield machine cutter head, namely X1, X2, X3, X4, and X5.

[0085] Extracting the comprehensive evaluation anomaly index: After preliminary analysis and calculation of the static (such as tool wear and surface defects) and dynamic (such as temperature rise and vibration) indicators of each area, the comprehensive evaluation anomaly index of area X1 was 8.5, area X2 was 7.0, area X3 was 8.0, area X4 was 6.5, and area X5 was 9.0.

[0086] Comparison and sorting: After comparing these indices, sort them from large to small as follows: X5 (9.0) > X1 (8.5) > X3 (8.0) > X2 (7.0) > X4 (6.5).

[0087] Grading and Area Determination: If a pre-defined comprehensive assessment abnormality index greater than 8.0 indicates a high-risk level, the corresponding area is designated as a risk zone; a value between 6.0 and 8.0 indicates a potential for deformation, and the corresponding area is designated as a deformation zone. Therefore, areas X5 and X1 are designated as risk zones, while areas X2, X3, and X4 are designated as deformation zones. Construction personnel can focus on risk areas, prioritizing inspection and maintenance of areas X5 and X1 to promptly address potential issues.

[0088] It should be noted that the present invention identifies deformation areas and risk areas based on a correlation model between dynamic loads and static deformations. It can accurately identify deformation areas and divide risk levels, achieve early risk prediction and proactive maintenance, break through the traditional limitation of only detecting deformed states, and significantly improve the foresight and reliability of cutterhead health management.

[0089] See also Figure 2 As shown, the second aspect of the present invention provides a method for detecting deformation of the central area of the cutter head of a shield machine, including: S1, area division: based on the three-dimensional structural characteristics of the central area of the cutter head of the target shield machine, a geometric grid division algorithm is used to generate monitoring areas with equal density distribution and generate unique codes, and the center point of each monitoring area is used as a monitoring point.

[0090] S2. Static monitoring: Use a 3D laser scanning device to scan the 3D topography data of each monitoring area in real time, perform point cloud registration and comparison with the pre-stored initial 3D data, use image processing algorithms to achieve quantitative analysis of tool wear and cutterhead surface defect assessment, and further output a static anomaly index.

[0091] S3. Dynamic monitoring: Integrate infrared thermal imaging devices, vibration sensor groups and soil slag image acquisition devices to collect temperature rise gradients, vibration spectrum characteristics and shield machine soil slag discharge images of each monitoring area in real time, and calculate the dynamic anomaly index through a multi-source data fusion model.

[0092] S4. Abnormal identification: A distributed stress sensor network embedded in monitoring points in a dot matrix arrangement is used to obtain the stress distribution matrix in real time and perform differential calculation with the preset reference stress field matrix. The abnormality judgment threshold is dynamically corrected, and abnormality identification is performed based on the static abnormality index and dynamic abnormality index.

[0093] S5. Deformation positioning: Locate and output the deformed area and risk area based on the abnormality recognition results.

[0094] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. A shield machine cutterhead center area deformation detection system, characterized in that: include: Region division module: Based on the three-dimensional structural characteristics of the target shield machine cutterhead center area, a geometric mesh division algorithm is used to generate monitoring areas with equal density distribution and generate unique codes. The center point of each monitoring area is used as the monitoring point; Static monitoring module: Utilizes a 3D laser scanner to scan the 3D topography data of each monitoring area in real time, performs point cloud registration and comparison with pre-stored initial 3D data, and uses image processing algorithms to quantitatively analyze tool wear and assess cutterhead surface defects, further outputting a static anomaly index. Dynamic monitoring module: Integrates infrared thermal imaging devices, vibration sensor groups, and 3D scanning devices to monitor the temperature rise gradient, vibration spectrum characteristics, and shield machine soil and slag discharge morphological parameters of each monitoring area in real time, and calculates the dynamic anomaly index through a multi-source data fusion model; Anomaly Identification Module: This module uses a distributed stress sensor network embedded in monitoring points in a dot matrix arrangement to obtain the stress distribution matrix in real time and performs differential calculations with the preset reference stress field matrix. It dynamically adjusts the anomaly judgment threshold and simultaneously identifies anomalies based on static and dynamic anomaly indices. Deformation positioning module: locates and outputs deformation areas and risk areas based on anomaly recognition results; The specific method of dynamically correcting the abnormality determination threshold is as follows: The stress distribution matrix obtained in real time is differentially calculated with the preset reference stress field matrix to obtain the stress deviation matrix of the shield machine center area, and then compared with the preset reference stress deviation threshold to obtain the abnormal judgment threshold correction coefficient of each monitoring point; Constructing a modified abnormality determination threshold for each monitoring area based on the abnormality determination threshold correction coefficient of each monitoring point and the initially set abnormality determination threshold; The specific analysis method for calculating the dynamic anomaly index through the multi-source data fusion model is as follows: Construct the temperature rise anomaly index, vibration frequency anomaly index and shield machine soil discharge morphology anomaly index for each monitoring area; The abnormal indices are fused and analyzed to obtain the dynamic abnormal index of each monitoring area, wherein the temperature rise abnormal index and the vibration frequency abnormal index are for the actual situation of each monitoring area, and the shield machine's soil slag discharge morphology abnormal index is for the actual situation of the entire shield machine; The soil slag discharge morphological parameters of the shield machine collected by the three-dimensional scanning device are used to evaluate the soil slag discharge volume and soil slag particle size distribution during the shield machine's soil slag discharge process, and then a comparative analysis is performed to obtain the soil slag discharge morphological anomaly index of the shield machine.

2. A shield machine cutterhead center area deformation detection system according to claim 1, characterized in that: The specific analysis process of the tool wear quantitative analysis is as follows: The actual volume of each tool is obtained based on the three-dimensional topography data of each monitoring area obtained by real-time scanning using a three-dimensional laser scanning device. This is then compared with the initial volume of each tool and combined with wear analysis to obtain the wear index of each tool. A number of wear monitoring points are evenly distributed on the surface of each tool to obtain the corresponding monitoring thickness. Then, the monitoring thickness of each tool surface corresponding to each wear monitoring point is compared and analyzed to obtain the wear heterogeneity index of each tool. The wear index and wear heterogeneity index of each tool are averaged to obtain the wear quantitative evaluation index of each tool; Obtain the projection position of each tool on the cutterhead surface, identify the one or more monitoring areas to which these projections belong, and compile a list of tools corresponding to each monitoring area; The tool wear evaluation index of each monitoring area is obtained by calculating the average of the wear quantitative evaluation index of each tool in each monitoring area.

3. A shield machine cutterhead center area deformation detection system according to claim 1, characterized in that: The specific analysis process of the cutter head surface defect evaluation is as follows: The three-dimensional morphological data of each monitoring area obtained in real time by a three-dimensional laser scanning device is used to determine the number of surface defects and their actual area in each monitoring area, which are then compared with the pre-set reference defect number and reference defect area, and the mean value is calculated and analyzed to obtain the cutter head surface defect evaluation index of each monitoring area.

4. A shield machine cutterhead center area deformation detection system according to claim 1, characterized in that: The specific method of constructing the temperature rise anomaly index and vibration frequency anomaly index of each monitoring area is as follows: Calculate the average temperature of adjacent monitoring points as the reference temperature, then compare the temperature of each monitoring point with the reference temperature to analyze and obtain the temperature rise anomaly index of each monitoring area; The specific analysis method of the vibration frequency anomaly index refers to the specific analysis method of the temperature rise anomaly index.

5. A shield machine cutterhead center area deformation detection system according to claim 4, characterized in that: The specific analysis method for evaluating the discharge volume and particle size distribution of the shield machine's soil slag discharge process is as follows: Based on the shield machine soil slag discharge morphological parameters provided by the three-dimensional scanning device, multiple batches of data extraction and processing are performed within a unit time interval to determine the volume of each batch of soil slag; The actual discharge amount of soil slag of each batch is calculated by combining the volume of soil slag of each batch with the density of soil slag; Conduct a fluctuation analysis on the soil slag discharge volume of the latest batch and the previous batches to obtain the evaluation results of the soil slag discharge fluctuation; The soil debris is segmented into particles based on the point cloud segmentation algorithm to obtain the volume of each soil debris particle. Based on this, an equivalent diameter analysis is performed to obtain the equivalent diameter of each soil debris particle, and then a three-dimensional particle size distribution map is constructed. The proportion of soil debris particles in the pre-set expected particle size range is obtained and a difference analysis is performed with the pre-set reference expected particle size proportion to obtain the evaluation results of soil debris particle size distribution anomalies.

6. A shield machine cutterhead center area deformation detection system according to claim 1, characterized in that: The specific method of performing abnormality identification is as follows: The weighted sum of the static anomaly index and the dynamic anomaly index of each monitoring area is calculated to obtain the comprehensive evaluation anomaly index of each monitoring area; The comprehensive evaluation abnormality index of each monitoring area is compared with the corresponding modified abnormality judgment threshold. If the comprehensive evaluation abnormality index of a monitoring area is greater than the corresponding modified abnormality judgment threshold, it is judged that there is an abnormality in the monitoring area and it is recorded as an abnormal monitoring area. Otherwise, it is judged that there is no abnormality in the monitoring area.

7. The shield machine cutterhead center area deformation detection system according to claim 1, characterized in that: The specific method of locating and outputting the deformation area and risk area is as follows: Arrange the comprehensive abnormality index of each abnormal monitoring area in descending order, classify it into deformation area and risk area according to the risk index, and output the corresponding area number.

8. A method for detecting deformation of a shield machine cutterhead center region, performed by the shield machine cutterhead center region deformation detection system according to any one of claims 1 to 7, characterized in that: include: S1. Area division: Based on the three-dimensional structural characteristics of the target shield machine cutterhead center area, a geometric meshing algorithm is used to generate monitoring areas with equal density distribution and generate unique codes. The center point of each monitoring area is used as the monitoring point. S2. Static Monitoring: Utilize a 3D laser scanner to scan the 3D topography data of each monitoring area in real time, perform point cloud registration and comparison with pre-stored initial 3D data, and use image processing algorithms to quantitatively analyze tool wear and assess cutterhead surface defects, further outputting a static anomaly index. S3. Dynamic monitoring: Integrating infrared thermal imaging devices, vibration sensor groups, and soil and slag image acquisition devices to collect temperature rise gradients, vibration spectrum characteristics, and shield machine soil and slag discharge images in real time in each monitoring area, and calculating dynamic anomaly indexes through a multi-source data fusion model; S4. Abnormal identification: A distributed stress sensor network embedded in monitoring points in a dot matrix arrangement is used to obtain the stress distribution matrix in real time and perform differential calculations with the preset reference stress field matrix. The abnormality judgment threshold is dynamically modified, and abnormality identification is performed based on the static abnormality index and dynamic abnormality index. S5. Deformation positioning: Locate and output the deformed area and risk area based on the abnormality recognition results.

Images