A warning method for damage of the side cutter of a shield TBM

Abstract

The present invention discloses a method for early warning of damage to the side cutters of shield TBM cutters, which relates to the technical field of shield TBM construction. It includes a shield TBM construction historical data workstation, a shield TBM construction site collector, a shield TBM construction site receiver, and a side cutter damage early warning system for shield TBM cutters. According to the characteristics of on-site construction data, the present invention realizes real-time early warning of damage to the side cutters of earth pressure balance shields, slurry balance shields, and TBM cutters through the analysis of real-time construction data. According to the comprehensive changes in parameters such as tunneling speed, thrust, torque, and penetration, it realizes real-time and rapid judgment of damage to the side cutters of shield TBM cutters. By making associated judgments on time, ring number, and mileage, the accuracy of marked data is ensured. Through the fault tolerance processing of characteristic data items, the robustness and fault tolerance ability of the algorithm system are realized, providing more rapid and timely early warning of damage to the side cutters of shield TBM for shield TBM construction personnel.

Description

Technical Field

[0001] The present invention relates to the technical field of shield TBM construction, and particularly to a method for warning of damage to the side cutter of a shield TBM Background Art

[0002] With the development of the economy, the demand for tunnel projects such as urban subways, railway tunnels, South-to-North Water Diversion, and West-to-East Gas Transmission is gradually increasing. Considering factors such as construction quality, construction cost, and construction period, more and more tunnel projects choose the shield TBM construction method. Shield TBM construction has the advantages of high construction quality, high controllability of the construction period, and high degree of construction automation, so it has been widely used in the construction of mined tunnels

[0003] During the construction process of shield TBM, the side cutter of the cutterhead often gets damaged. Since the cutter is a moving part and directly contacts the soil or rock mass in the face area, it is very easy to cause damage such as eccentric wear and rupture of the cutter. The damage of the side cutter of the cutterhead will cause a decrease in the rock cutting ability of the shield TBM, and local damage will cause abnormal changes in the cutterhead rotation speed, cutterhead torque, shield propulsion speed, and propulsion force, resulting in an increase in energy consumption during the shield tunneling process, deviation in attitude control, and difficulty in shield driving

[0004] Since it is impossible to directly obtain the damage information of the cutters in the face area, installing sensors in the face area faces the problems of difficult signal transmission and the sensors being extremely easy to be damaged and lose their effectiveness. The damage of the side cutter of the cutterhead includes slow superimposed damage and sudden fracture. Based on the real-time construction data of the shield TBM, the warning of the damage of the side cutter of the cutterhead can judge and warn the damage situation of the side cutter of the shield TBM without adding sensors

[0005] In order to effectively solve the problem that the side cutter of the cutterhead is damaged and difficult to detect during the construction process of shield TBM, a warning system and method for the damage of the side cutter of the shield TBM cutterhead are designed, which can realize the real-time and rapid discovery of whether the side cutter of the cutterhead is damaged and the damage state during the shield construction process, and reduce the impact of abnormal events Summary of the Invention

[0006] The purpose of the present invention is to provide a method for warning of damage to the side cutter of a shield TBM in order to solve the above problems

[0007] The present invention realizes the above purpose through the following technical solutions

[0008] A method for warning of damage to the side cutter of a shield TBM includes the following steps

[0009] Step S1: Extract historical data according to the ring number, time, and screen the shield construction status

[0010] Step S2: Detect the start segment and stable segment of the historical data, detect the number of point groups, eliminate overly short data segments, and then detect whether the historical data volume meets the equivalent requirements with respect to time, ring number, and mileage;

[0011] Step S3: Judge the data behavior, and obtain data distribution information such as the percentile, mode, data deviation band range, and outlier distribution characteristics of the equivalent historical data;

[0012] Step S4: Perform absolute quantity limit cleaning based on equipment characteristics and relative quantity cleaning based on continuous data rules on the historical data, perform corresponding smoothing processing on information such as the propulsion speed, propulsion force, cutter head torque, and penetration of the shield TBM, obtain the values of corresponding characteristic data such as the slope, fluctuation condition, and mean of each parameter, and obtain the basic health data characteristics and overall data trend;

[0013] Step S5: Judge information such as the type, diameter, and current state of the shield TBM;

[0014] Step S6: Establish a real-time data sliding window, extract the data of the previous 10 minutes, and accumulate it with the previous data;

[0015] Step S7: Perform absolute quantity data cleaning on the accumulated real-time data every minute, and at the same time discard part of the data at the end of the sliding window to maintain effective ten-minute sliding window data;

[0016] Step S8: Perform processing of characteristic data similar to the historical data on the real-time data, and obtain the values of corresponding characteristic data such as the slope, fluctuation condition, and mean of each parameter;

[0017] Step S9: Combine the damage criteria of the hob and side hob of the earth pressure shield, slurry shield, and TBM, judge whether an abnormal event of hob and side hob damage has occurred. If an abnormal event of hob and side hob damage has occurred, further judge the severity of the hob and side hob damage, and realize the real-time judgment of whether an abnormal event of hob and side hob damage has occurred during the shield construction process.

[0018] Preferably: The specific steps of step S1 include: extracting the historical data ring by ring according to the ring number and judging the shield construction state, and eliminating the data in the shutdown state; for the project with invalid ring numbers, extracting and converting the historical data according to the mileage, and judging the shield construction state; for the project with invalid ring numbers, extracting the historical data hour by hour according to the time, and judging the shield construction state.

[0019] Preferably: The specific steps of step S2 include: detecting and segmenting the start segment and stable segment of the extracted historical data based on data distribution characteristics, change point detection, and point group recognition; eliminating overly short data segments through point group number detection; detecting whether the historical data volume meets the equivalent requirements with respect to time, ring number, and mileage.

[0020] Preferably, the step S3 specifically includes: judging the data state, checking the normality of the data, analyzing the deviation of the normal distribution, statistically analyzing the distribution characteristics of historical data, and obtaining data distribution information such as the percentile, mode, data deviation band range, and outlier distribution characteristics of equivalent historical data.

[0021] Preferably, the step S4 specifically includes: performing absolute quantity limit cleaning on historical data based on equipment characteristics and the 3σ criterion, performing relative quantity cleaning on historical data based on the law of continuous data, performing corresponding smoothing processing on information such as the propulsion speed, propulsion force, cutterhead torque, and penetration of the shield TBM, and obtaining the values of corresponding characteristic data such as the slope, fluctuation condition, mean, median, and mode of each parameter, so as to obtain the basic health data characteristics and the overall data trend.

[0022] Preferably, the step S5 specifically includes: judging information such as the type, diameter, and current state of the shield TBM every minute, and performing real-time data judgment operations on the shield TBM in the tunneling state.

[0023] Preferably, the step S6 specifically includes: establishing a real-time data sliding window, extracting the data of the previous 10 minutes according to the current time every minute, accumulating the data with the previous data, intercepting the valid data during tunneling, and judging the data volume. When the first data extraction is insufficient, extract the data of the previous 10 seconds, judge the state and data volume until the extraction of 10 minutes of valid data is completed.

[0024] Preferably, the step S7 specifically includes: performing absolute quantity data cleaning on the accumulated real-time data every minute, performing data state judgment and data statistics on the valid data in the 10-minute window to obtain abnormal data after removing extremes, and discarding part of the data at the end of the sliding window to maintain the valid 10-minute sliding window data.

[0025] Preferably, the step S8 specifically includes: performing processing on the real-time data for characteristic data similar to the historical data, and extracting characteristic data from the processed real-time data, including data information such as the data change rate, median, mode, average value, and fluctuation range, to complete the processing of the current time window data similar to the historical data processing.

[0026] Preferably, the step S9 specifically includes: combining the damage criteria of the hob and side hob of the earth pressure balance shield, slurry shield and TBM, judging whether an abnormal event of hob and side hob damage has occurred, and if an abnormal event of hob and side hob damage has occurred, further judging the severity of the hob and side hob damage, so as to realize the real-time judgment of whether an abnormal event of hob and side hob damage has occurred during the shield construction process.

[0027] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention can, according to the characteristics of on-site construction data, through the analysis of real-time construction data, realize the real-time early warning of the damage of the cutter head cutters of earth pressure balance shield tunneling machines, slurry balance shield tunneling machines and TBMs. According to the comprehensive changes of parameters such as tunneling speed, thrust, torque, and penetration degree, it can realize the real-time and rapid judgment of the damage of the cutter head cutters of shield TBMs. Through the associated judgment of time, ring number, and mileage, it can ensure the accuracy of the marked data. Through the fault tolerance processing of characteristic data items, it can realize the robustness and fault tolerance ability of the algorithm system, and provide a faster and more timely early warning of the damage of the cutter head cutters of shield TBMs to the construction personnel of shield TBMs. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0029] Figure 1 FIG. is a schematic flow chart of a method for early warning of the damage of the cutter head cutters of a shield TBM according to the present invention.

[0030] Figure 2 FIG. is a structural block diagram of an early warning system used for the method for early warning of the damage of the cutter head cutters of a shield TBM according to the present invention.

[0031] The descriptions of the reference numerals are as follows:

[0032] 1. Data collector; 2. VPN encryption channel; 3. Cache server; 4. Historical data workstation; 5. SQLServer server; 6. Web server; 7. On-site receiving end; 8. Early warning system for the damage of the cutter head cutters of a shield TBM. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and the like are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first", "second", and the like may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0034] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installation", "connection" and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal connection of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood by specific circumstances.

[0035] The present invention will be further described below in conjunction with the accompanying drawings:

[0036] like Figure 1 - Figure 2 As shown, a shield TBM cutter edge cutter damage early warning method comprises the following steps:

[0037] Step S1: extract historical data by ring number, time and shield construction status;

[0038] Step S2: Perform startup segment and stable segment detection and point group quantity detection on the historical data, remove too short data segments, and then detect whether the amount of historical data meets the equivalent requirements relative to time, ring number, and mileage;

[0039] Step S3: judging the data properties, obtaining data distribution information such as percentile points, mode, data deviation band range, and isolated point distribution characteristics of equivalent historical data;

[0040] Step S4: Perform absolute quantity limit cleaning based on equipment characteristics and relative quantity cleaning based on continuous data rules on historical data, perform corresponding smoothing on information such as shield TBM propulsion speed, propulsion force, cutter head torque and penetration, obtain the values ​​of corresponding characteristic data such as slope, fluctuation, mean value of each parameter, and obtain basic health data characteristics and overall data trends;

[0041] Step S5: Determine the type, diameter, current status and other information of the shield TBM;

[0042] Step S6: Establish a real-time data sliding window, extract data from 10 minutes forward, and accumulate it with the previous data;

[0043] Step S7: Perform absolute data cleaning on the accumulated real-time data every one minute, discard some data at the end of the sliding window, and keep valid ten-minute sliding window data;

[0044] Step S8: Performing feature data processing similar to historical data on real-time data to obtain values ​​of corresponding feature data such as slope, fluctuation, mean, etc. of various parameters;

[0045] Step S9: Combine the cutter and side cutter damage judgment criteria of the earth pressure shield, slurry shield and TBM to determine whether an abnormal event of cutter and side cutter damage has occurred. If an abnormal event of cutter and side cutter damage has occurred, then determine the severity of the cutter and side cutter damage, so as to realize real-time judgment of whether an abnormal cutter and side cutter damage has occurred during shield construction.

[0046] Among them, step S1 specifically includes: extracting historical data ring by ring number and judging the shield construction status, and eliminating data in the shutdown state; for projects with invalid ring numbers, extracting and converting historical data according to mileage, and judging the shield construction status; for projects with invalid ring numbers, extracting historical data hour by hour by time, and judging the shield construction status.

[0047] The step of normalizing and extracting historical data includes:

[0048] a. Extract one ring of equivalent data from the historical data of tunnel construction;

[0049] b. Determine whether the time interval is greater than 24h or the ring number is greater than 4 rings;

[0050] c. If step b is not met, determine whether the current data volume, ring number, and timestamp meet the two-ring equivalent data requirements;

[0051] d. If step c is not satisfied, repeat steps a, b, and c and continue to extract until two-ring equivalent data are extracted;

[0052] e. If step b is satisfied, terminate the extraction of historical data in this round, wait for the ring number to be updated, and then extract historical data again, and repeat steps a, b, c, and d;

[0053] The specific steps of step S2 include: detecting and segmenting the start segment and the stable segment of the extracted historical data based on data distribution characteristics, change point detection, and point group recognition; removing overly short data segments through point group quantity detection; and detecting whether the amount of historical data meets the equivalent requirements with respect to time, ring number, and mileage.

[0054] The specific steps of step S3 include: judging the data behavior, checking the normality of the data, analyzing the deviation of the normal distribution, statistically analyzing the distribution characteristics of the historical data, and obtaining data distribution information such as the percentile, mode, data deviation band range, and outlier distribution characteristics of the equivalent historical data.

[0055] The specific steps of step S4 include: cleaning the absolute quantity of the historical data based on the equipment characteristics and the 3σ criterion, cleaning the relative quantity of the historical data based on the continuous data law, performing corresponding smoothing processing on information such as the propulsion speed, propulsion force, cutter head torque, and penetration of the shield TBM, obtaining the values of corresponding characteristic data such as the slope, fluctuation condition, mean, median, and mode of each parameter, and obtaining the basic health data characteristics and the overall data trend.

[0056] The steps for normalizing and cleaning the historical data include:

[0057] Judging the normality of the historical data and analyzing the deviation degree of the data from the normal distribution; then performing gross error processing and analyzing the statistical characteristics of the historical data to obtain the healthy historical data after cleaning.

[0058] The specific steps of step S5 include: judging information such as the type, diameter, and current status of the shield TBM every minute, and performing real-time data judgment operations on the shield TBM in the tunneling state.

[0059] The specific steps of step S6 include: establishing a real-time data sliding window. Every minute, according to the current time, extract the data of the previous 10 minutes, accumulate it with the previous data, intercept the valid data in the tunneling, and judge the data volume. When the first extraction of data is insufficient, extract the data of the previous 10 seconds, judge the status and the data volume until the extraction of 10 minutes of valid data is completed.

[0060] The specific steps of step S7 include: performing absolute quantity data cleaning on the accumulated real-time data every minute, performing data behavior judgment and data statistics on the valid data in the 10-minute window to obtain the abnormal data with extreme values removed, and at the same time discarding part of the data at the end of the sliding window to maintain the valid 10-minute sliding window data.

[0061] The specific steps of S8 include: processing the real-time data into characteristic data similar to the historical data, and extracting the characteristic data from the processed real-time data, including data information such as data change rate, median, mode, average value, fluctuation range, etc., to complete the processing of the current time window data which is approximately the same as the historical data processing.

[0062] The specific steps of S9 include: combining the damage criteria of the hob and side cutter of earth pressure shield, slurry shield and TBM, judging whether an abnormal event of hob and side cutter damage has occurred. If an abnormal event of hob and side cutter damage has occurred, further judge the severity of the hob and side cutter damage, so as to realize the real-time judgment of whether an abnormal event of hob and side cutter damage has occurred during the shield construction process.

[0063] The hob and side cutter damage warning system can realize the real-time warning of the damage of the hob and side cutter of earth pressure balance shield, slurry balance shield and TBM according to the characteristics of on-site construction data, historical data and the current state of the shield, and realize the real-time and rapid judgment of the damage of the hob and side cutter of the shield TBM according to the comprehensive changes of parameters such as tunneling speed, thrust, torque and penetration.

[0064] The method in the embodiment of the present invention will be described in detail below in conjunction with specific embodiments.

[0065] Step 1: Conduct expert analysis and on-site verification on the typical historical data of multiple lines, program and set the characteristics and applicable conditions of the historical data, and store them in the database to form the damage criteria of the hob and side cutter. Some examples are as follows:

[0066] Equipment type: TBM

[0067] Shield diameter: 10330mm

[0068] Geological type: hard rock

[0069] Parameter 1: One hob is eccentrically worn within the first 100mm, and there is no obvious abnormal situation; when two hobs are eccentrically worn, the tunneling speed gradually decreases.

[0070] Parameter 2: Within 100mm, the thrust change is larger compared with the damage of the center cutter; when three side cutters are eccentrically worn, the thrust exceeds the previous 10 minutes, and the thrust increases by 2000 - 3000KN.

[0071] Parameter 3: Within 100mm, the torque change is large, and when three are damaged, the torque change range gradually increases.

[0072] Parameter 4: Within 100mm, the penetration has no obvious abnormal change. When 100 < X ≤ 500mm, it decreases by 3 - 5mm / r.

[0073] Step 2: Extract the historical data ring by ring according to the ring number and judge the shield construction status, and eliminate the data in the shutdown state; for projects with invalid ring numbers, extract and transform the historical data according to the mileage, and judge the shield construction status; for projects with invalid ring numbers, extract the historical data hour by hour and judge the shield construction status.

[0074] Step 3: Detect and segment the start-up section and the stable section of the extracted historical data based on the data distribution characteristics, change point detection, and point group recognition; eliminate the too short data segments through the point group quantity detection; detect whether the historical data volume meets the equivalent requirements relative to time, ring number, and mileage.

[0075] Step 4: Judge the data behavior, check the normality of the data, analyze the deviation of the normal distribution, statistically analyze the distribution characteristics of the historical data, and obtain data distribution information such as the percentile, mode, data deviation band range, and outlier distribution characteristics of the equivalent historical data.

[0076] Step 5: Clean the historical data based on the equipment characteristics and the 3σ criterion for absolute quantity limitation, perform relative quantity cleaning on the historical data based on the continuous data law, perform corresponding smoothing processing on information such as the shield TBM propulsion speed, propulsion force, cutter head torque, and penetration, and obtain the slope, fluctuation condition, mean, median, mode, etc. of each parameter. Obtain the basic health data characteristics and the overall data trend.

[0077] Step 6: Judge the information such as the type, diameter, and current status of the shield TBM every minute, and perform real-time data judgment operations on the shield TBM in the tunneling state.

[0078] Step 7: Establish a real-time data sliding window. Every minute, according to the current time, extract the data of the previous 10 minutes, accumulate it with the previous data, intercept the valid data in the tunneling, and judge the data volume. When the first data extraction is insufficient, extract the data of the previous 10 seconds, judge the status and data volume until the extraction of 10 minutes of valid data is completed.

[0079] Step 8: Perform absolute quantity data cleaning on the accumulated real-time data every minute. For the valid data in the 10-minute window, perform data behavior judgment and data statistics to obtain the extreme abnormal data removed, and at the same time discard part of the data at the end of the sliding window to maintain the valid 10-minute sliding window data.

[0080] Step 9: Perform characteristic data processing on the real-time data similar to the historical data, and extract the characteristic data from the processed real-time data, including data change rate, median, mode, average value, fluctuation range, etc. Complete the processing of the current time window data similar to the historical data processing.

[0081] Step 10: Combine the damage criteria of the hob and side hob of earth pressure shield, slurry shield and TBM, and determine whether an abnormal event of hob and side hob damage has occurred. If an abnormal event of hob and side hob damage has occurred, further determine the severity of the hob and side hob damage, so as to realize the real-time judgment of whether an abnormal hob and side hob damage has occurred during the shield construction process.

[0082] The warning system used in the above method for warning of damage to the side cutter of the shield TBM hob includes a data collector 1, a VPN encryption channel 2, a cache server 3, a historical data workstation 4, an SQL Server server 5, a web server 6, a field receiving end 7, and a warning system 8 for damage to the side cutter of the shield TBM hob. The data collector 1 is electrically connected to the VPN encryption channel 2, the VPN encryption channel 2 is electrically connected to the cache server 3, the cache server 3 is electrically connected to the historical data workstation 4, the historical data workstation 4 is electrically connected to the SQL Server server 5, the cache server 3, the historical data workstation 4, and the SQL Server server 5 are respectively electrically connected to the warning system 8 for damage to the side cutter of the shield TBM hob, the warning system 8 for damage to the side cutter of the shield TBM hob is electrically connected to the web server 6, and the web server 6 is electrically connected to the field receiving end 7; the shield TBM construction data is collected by the black box of the data collector 1 and transmitted to the cache server 3 through the VPN encryption channel 2. The cache server 3 uses two Intel(R) Xeon(R) CPU E5-2650 v4 @2.20GHz processors and is equipped with 128GB of memory, and buffers the real-time data to the historical data workstation 4 for storage. The historical data workstation 4 uses two Intel(R) Xeon(R) CPU E5-2698R v4 @2.20GHz server processors, has 128GB of memory, and a distributed storage cluster with a hard disk storage capacity of 80TB to meet the storage and transfer of data; then the business data is submitted to the SQL Server server 5 for storage of business data; the SQL Server server 5 is equipped with two Intel(R) Xeon(R) CPU E5-2650 v4 @2.20GHz processors and is equipped with 128GB of memory; it reads the current data of this shield line in the cache server 3 every minute, reads the historical data in the database of the historical data workstation 4, combines the geological data and shield machine parameters and other data in the SQL Server server 5, obtains a set of characteristic data of the historical data through data analysis and processing, judges the damage to the side cutter of the shield TBM hob according to the shield state and real-time data, and stores this data in the database in the web server 6 for web access by the field receiving end 7; among them, both the web server 6 and the field receiving end 7 use two Intel(R) Xeon(R) CPU E5-2650 v4 @2.20GHz processors and are equipped with 128GB of memory.

[0083] In summary:

[0084] The present invention realizes real-time early warning of damage to the cutter head cutters of earth pressure balance shield machines, slurry balance shield machines, and TBMs by analyzing real-time construction data according to the characteristics of on-site construction data of shield TBMs.

[0085] The present invention realizes the summary and program implementation of the criterion for judging the damage of the cutter head cutters of shield TBMs based on the comprehensive changes of parameters such as tunneling speed, thrust force, torque, and penetration degree.

[0086] The present invention combines historical data, real-time data, and the criterion for judging the damage of the cutter head cutters, ensuring the adaptability of the algorithm to shield TBMs of different types and different lines and the accuracy of recommendations. At the same time, through the fault tolerance processing of characteristic data items, the robustness and fault tolerance ability of the algorithm system are realized, providing more rapid and timely early warning of the damage of the cutter head cutters of shield TBMs to the construction personnel of shield TBMs.

[0087] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0088] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can be provided with these computer program instructions to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0089] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means realizes the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0090] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the process Figure 1 one process or multiple processes and / or blocks Figure 1 steps for implementing the functions specified in one block or multiple blocks.

[0091] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the spirit and scope of the present invention as protected by the claims. These all fall within the protection scope of the present invention

[0092] The basic principles, main features and advantages of the present invention have been shown and described above. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the description in the specification only illustrate the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed.

Claims

1. A warning method for the damage of the side hob of a shield TBM cutter, characterized in that: The following steps are involved: Step S1: extract historical data by ring number, time and shield construction status; Step S2: Perform startup segment and stable segment detection and point group quantity detection on the historical data, remove too short data segments, and then detect whether the amount of historical data meets the equivalent requirements relative to time, ring number, and mileage; Step S3: judge the data properties and obtain the percentile, mode, data deviation band range, and isolated point distribution characteristics of the equivalent historical data; Step S4: Perform absolute quantity limit cleaning based on equipment characteristics and relative quantity cleaning based on continuous data rules on historical data, perform corresponding smoothing on the TBM propulsion speed, propulsion force, cutter head torque and penetration, obtain the slope, fluctuation and mean value of each parameter, and obtain basic health data characteristics and overall data trends; Step S5: Determine the type, diameter and current state of the shield TBM; Step S6: Establish a real-time data sliding window, extract data for 10 minutes forward, and accumulate it with the previous data; Step S7: Perform absolute data cleaning on the accumulated real-time data every one minute, discard some data at the end of the sliding window, and keep valid ten-minute sliding window data; Step S8: Perform feature data processing similar to historical data on real-time data to obtain the slope, fluctuation, and mean value of each parameter; Step S9: Combine the cutter and side cutter damage judgment criteria of the earth pressure shield, slurry shield and TBM to determine whether an abnormal event of cutter and side cutter damage has occurred. If an abnormal event of cutter and side cutter damage has occurred, then determine the severity of the cutter and side cutter damage, so as to realize real-time judgment of whether an abnormal cutter and side cutter damage has occurred during shield construction.

2. A method for early warning of damage to the side cutter of a shield TBM hob according to claim 1, characterized in that: The step S1 specifically includes: Historical data are extracted ring by ring number to determine the shield construction status, and data in the shutdown state are eliminated; for projects with invalid ring numbers, historical data are extracted and converted by mileage, and the shield construction status is determined; for projects with invalid ring numbers, historical data are extracted hour by hour by time, and the shield construction status is determined.

3. A method for early warning of damage to the side hob of a shield TBM hob according to claim 1, characterized in that: The step S2 specifically includes: The extracted historical data is segmented into startup and stable segments based on data distribution characteristics, change point detection and point group recognition. The too short data segments are eliminated through point group quantity detection. The historical data volume is tested to see whether it meets the equivalent requirements relative to time, ring number and mileage.

4. A method for early warning of the damage of the side cutter of a shield TBM hob according to claim 1, characterized in that: The step S3 specifically includes: Judge the data properties, check the normality of the data, analyze the normal distribution deviation, statistically analyze the distribution characteristics of historical data, and obtain the percentile, mode, data deviation band range, and isolated point distribution characteristics of equivalent historical data.

5. A method for early warning of damage to the side hob of a shield TBM hob according to claim 1, characterized in that: The step S4 specifically includes: The historical data are cleaned with absolute quantity restrictions based on equipment characteristics and the 3σ criterion, and the historical data are cleaned with relative quantity based on the rules of continuous data. The TBM propulsion speed, propulsion force, cutter torque and penetration are smoothed accordingly, and the slope, fluctuation, mean, median and mode values ​​of various parameters are obtained to obtain the basic health data characteristics and overall data trends.

6. A method for early warning of the damage of the side hob of a shield TBM hob according to claim 1, characterized in that: The step S5 specifically includes: Judge the type, diameter and current status of the shield TBM every minute, and perform judgment operations on the real-time data of the shield TBM in the tunneling state.

7. A method for early warning of damage to the side hob of a shield TBM hob according to claim 1, characterized in that: The specific steps of step S6 include: Establish a real-time data sliding window. Every minute, according to the current time, extract the data of the previous 10 minutes, accumulate it with the previous data, intercept the valid data in tunneling, and judge the data volume. When the first data extraction is insufficient, extract the data of the previous 10 seconds, judge the status and data volume until the extraction of 10 minutes of valid data is completed.

8. A method for early warning of the damage of the side hob of a shield TBM hob according to claim 1, characterized in that: The specific steps of step S7 include: Perform absolute data cleaning on the accumulated real-time data every minute. For the valid data in the 10-minute window, judge the data behavior and perform data statistics to obtain the abnormal data after removing the extreme values. At the same time, discard part of the data at the end of the sliding window to maintain the valid 10-minute sliding window data.

9. A method for early warning of the damage of the side cutter of a shield TBM hob according to claim 1, characterized in that: The specific steps of step S8 include: Perform processing on the feature data similar to the historical data for the real-time data, and extract the feature data from the processed real-time data, including the data change rate, median, mode, average value, and fluctuation range, to complete the processing of the current time window data similar to the historical data processing.

Images