Shield machine cutter cake diagnosis method and system based on historical operation data

Abstract

The application provides a shield machine cutter mud cake diagnosis method and system based on historical operation data, comprising: step 1: collecting state parameters in the tunneling process of the shield machine, and extracting working state data of the shield machine; step 2: pre-processing the state data, eliminating data not meeting preset requirements, and obtaining a shield machine operation parameter sequence for analysis; step 3: normalizing the pre-processed data by using the minimum-maximum method; step 4: calculating a mud cake discrimination index value of each time after normalization by using a discrimination formula; and step 5: setting a threshold according to the calculated discrimination index value, and estimating the mud cake occurrence time. The application realizes the judgment of the mud cake occurrence time under the condition that the shield machine operation data is complete, is beneficial to the related enterprises to adjust the operation strategy and operation parameters of the shield machine based on the data analysis result, timely discovers the suspected mud cake condition and removes the mud cake as soon as possible, and improves the construction efficiency of the shield machine.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of parameter evaluation, in particular to a shield cutter mud cake diagnosis method and system based on historical operation data. BACKGROUND

[0002] With the rapid development of China's economy, tunnel construction has become an important part of China's infrastructure construction, and shield is the representative of high-end tunnel boring equipment. In the process of shield tunneling, due to the adhesion of soil on the surface of the cutter head, it is easy to cause the cutter head to form a mud cake, which seriously affects the construction efficiency. When the shield machine works for a long time under the condition of mud cake adhesion, it may even cause serious damage to the key components such as the cutter head. As the underground engineering equipment is becoming increasingly intelligent, it is no longer a problem to obtain the operation parameters of the shield machine. Effective use of the collected shield machine operation parameters to diagnose the time of mud cake formation is beneficial to help engineering and technical personnel to discover the mud cake condition as soon as possible and remove the mud cake in time, so as to ensure the safe and efficient tunneling.

[0003] At present, the detection method for mud cake is mostly started from a few parameters, and the occurrence of mud cake is diagnosed by studying the change rule of these parameters. Patent document CN108548604A diagnoses mud cake by monitoring the temperature of the cutter head, and patent document CN113107499A diagnoses mud cake by evaluating the cutter head speed and motor output torque. These methods use relatively few parameters and do not fully exploit the tunneling parameters of the shield machine.

[0004] Patent document CN111622766A starts from multiple tunneling parameters and proposes a mud cake discrimination method, but the application of data is still analyzed one by one, the parameters are not grasped as a whole, the analysis process is relatively cumbersome, and the correlation between multiple data cannot be fully exploited.

[0005] In view of the deficiencies of the existing mud cake diagnosis method, a shield cutter mud cake diagnosis method based on historical operation data is proposed, which is beneficial to realize simple and accurate diagnosis of the shield cutter mud cake. SUMMARY

[0006] In view of the defects in the prior art, the purpose of the present application is to provide a shield cutter mud cake diagnosis method and system based on historical operation data.

[0007] The shield cutter mud cake diagnosis method based on historical operation data provided by the present application comprises:

[0008] Step 1: Collecting state parameters in the process of shield tunneling, and extracting working state data of the shield machine;

[0009] Step 2: preprocessing the state data, eliminating data not meeting the preset requirements, obtaining the shield machine running parameter sequence for analysis;

[0010] Step 3: normalizing the preprocessed data by using the minimum-maximum method;

[0011] Step 4: calculating the mud cake discrimination index value of each time after normalization by using the discrimination formula;

[0012] Step 5: setting a threshold according to the calculated discrimination index value to estimate the mud cake occurrence time.

[0013] Preferably, the step 1 comprises:

[0014] Step 1.1: selecting the cutter head speed, cutter head torque, each group of oil cylinder advancing pressure, advancing speed average value, penetration, total advancing force, excavation bin pressure and working bin pressure data as the state parameters of the shield machine;

[0015] Step 1.2: selecting the data in which the cutter head speed, cutter head torque and penetration are all not 0 as the working state data of the shield machine.

[0016] Preferably, the step 2 comprises:

[0017] Step 2.1: taking the absolute value of the cutter head torque of the shield machine in the working state;

[0018] Step 2.2: setting a threshold to eliminate data not meeting the preset requirements, and the calculation formula of the threshold is:

[0019]

[0020] Wherein, T H,i is the upper threshold of the i th state parameter; T L,i is the lower threshold of the i th state parameter; Q 3,i and Q 1,i respectively represent the upper quartile and lower quartile of the i th state parameter in the working state;

[0021] Step 2.3: five-point sliding average processing is performed on the eliminated data, thereby obtaining the shield machine running parameter sequence for analysis.

[0022] Preferably, the discrimination formula in the step 4 is:

[0023]

[0024] wherein k represents the value of the calculated mud cake discrimination index; x1 represents the normalized cutter head rotating speed; x2 represents the normalized cutter head torque; x3-x8 represent the normalized cylinder thrust pressure of each group; x9 represents the normalized average thrust speed; x 10 represents the normalized penetration; x 11 represents the normalized total thrust force; x 12 -x 17 represents the normalized pressure of each excavation chamber; x 18 -x 19 represents the normalized pressure of each working chamber; i is a serial number.

[0025] Preferably, the step 5 comprises: selecting a threshold value according to the calculation result of the discrimination index, taking 5% of the maximum value of the calculated discrimination index, if it exceeds the range, it is determined that the mud cake occurs, if the threshold value is set higher, the more serious the mud cake condition is diagnosed to occur.

[0026] According to the present application, a shield machine cutter head mud cake diagnosis system based on historical operation data is provided, comprising:

[0027] Module M1: collecting state parameters in the shield machine tunneling process, and extracting working state data of the shield machine;

[0028] Module M2: preprocessing the state data, eliminating data not meeting the preset requirements, and obtaining a shield machine operation parameter sequence for analysis;

[0029] Module M3: normalizing the preprocessed data by using the minimum-maximum method;

[0030] Module M4: calculating the mud cake discrimination index value of each time after normalization by using the discrimination formula;

[0031] Module M5: setting a threshold value according to the calculated discrimination index value, and estimating the mud cake occurrence time.

[0032] Preferably, the module M1 comprises:

[0033] Module M1.1: selecting the cutter head rotating speed, cutter head torque, cylinder thrust pressure of each group, average thrust speed, penetration, total thrust force, excavation chamber pressure and working chamber pressure data as the state parameters of the shield machine;

[0034] Module M1.2: selecting data in which the cutter head rotating speed, cutter head torque and penetration are all not 0 as the working state data of the shield machine.

[0035] Preferably, the module M2 comprises:

[0036] Module M2.1: taking the absolute value of the cutter head torque of the shield machine in the working state;

[0037] Module M2.2: set the threshold value to eliminate data that does not meet the preset requirements, the calculation formula of the threshold value is:

[0038]

[0039] Wherein, T H,i is the upper limit of the threshold value of the i-th state parameter; T L,i is the lower limit of the threshold value of the i-th state parameter; Q 3,i and Q 1,i respectively represent the upper quartile and lower quartile of the i-th state parameter in the working state;

[0040] Module M2.3: the data after elimination is subjected to five-point moving average processing, so as to obtain the shield machine running parameter sequence for analysis.

[0041] Preferably, the discriminant formula in the module M4 is:

[0042]

[0043] Wherein, k represents the value of the calculated mud cake discriminant index; x1 represents the normalized cutter head speed; x2 represents the normalized cutter head torque; x3-x8 represents the normalized cylinder thrust pressure; x9 represents the normalized average thrust speed; x 10 represents the normalized penetration; x 11 represents the normalized total thrust; x 12 -x 17 represents the normalized pressure of each excavation chamber; x 18 -x 19 represents the normalized pressure of each working chamber; i is the serial number.

[0044] Preferably, the module M5 includes: selecting a threshold value according to the calculation result of the discriminant index, taking 5% of the maximum value of the calculated discriminant index, if it exceeds the range, it is determined that the mud cake occurs, if the threshold value is set higher, the more serious the mud cake condition when the mud cake is diagnosed to occur.

[0045] Compared with the prior art, the present application has the following beneficial effects:

[0046] (1) The present application selects 19 kinds of tunneling parameters of the shield machine, which can more comprehensively reflect the mud cake condition of the cutter head of the shield machine;

[0047] (2) The present application constructs a discriminant index for judging the mud cake condition of the shield machine based on the selected shield machine running parameters, so as to reflect the mutual relationship between the tunneling parameters, and the data is more fully utilized;

[0048] (3) The application proposes a mud cake diagnosis threshold selection method based on the calculation result of the discrimination index, which is simple to implement and helps the driver to find the mud cake condition of the cutter head in time and remove it in time, thereby ensuring the safety and efficiency of the tunneling process. BRIEF DESCRIPTION OF DRAWINGS

[0049] Other features, objects and advantages of the application will become more apparent from the following detailed description of non-limiting embodiments, made with reference to the accompanying drawings:

[0050] Figure 1 is a flow chart of the shield cutter head mud cake diagnosis method based on historical operation data proposed by the application;

[0051] Figure 2 is an image of the discrimination index and selected threshold value made by the shield cutter head mud cake diagnosis method based on historical operation data proposed by the application. DETAILED DESCRIPTION

[0052] The application will be described in detail below with specific embodiments. The following embodiments will help those skilled in the art to further understand the application, but do not limit the application in any form. It should be pointed out that, for those skilled in the art, without departing from the concept of the application, a number of changes and improvements can be made. These all belong to the protection scope of the application.

[0053] Example 1:

[0054] According to the long-term prediction method for the torque of the cutter head of a full-face tunnel boring machine provided by the application, the method comprises the following steps: step 1, collecting 19 state parameters in the tunneling process of the shield machine and extracting the working state data of the shield machine; step 2, pre-processing the data to eliminate extreme outliers, and obtaining the shield machine operation parameter sequence for analysis; step 3, normalizing the pre-processed data by using the minimum-maximum method; step 4, calculating the mud cake discrimination index value at each time after normalization by using a discrimination formula; and step 5, setting a threshold value according to the calculated discrimination index to estimate the occurrence time of the mud cake.

[0055] The state parameters selected in step 1 include the cutter head speed, the cutter head torque, the A group cylinder pushing pressure, the B group cylinder pushing pressure, the C group cylinder pushing pressure, the D group cylinder pushing pressure, the E group cylinder pushing pressure, the F group cylinder pushing pressure, the average pushing speed, the penetration, the total pushing force, the excavation chamber pressure 1#, the excavation chamber pressure 2#, the excavation chamber pressure 3#, the excavation chamber pressure 4#, the excavation chamber pressure 5#, the excavation chamber pressure 6#, the working chamber pressure 1# and the working chamber pressure 2#, and the standard for determining that the shield machine is in a working state is that the cutter head speed, the cutter head torque and the penetration are all not 0.

[0056] Step 2 includes: rejecting extreme abnormal data and five-point sliding average processing by setting threshold, the calculation formula is as follows:

[0057]

[0058] Wherein, T H,i is the upper limit of the threshold of the i-th state parameter, T L,i is the lower limit of the threshold of the i-th state parameter, Q 3,i and Q 1,i respectively represent the upper quartile and lower quartile of the i-th state parameter under working condition;

[0059] Step 3 includes: normalizing the preprocessed data, the calculation formula is as follows:

[0060]

[0061] Wherein, x i represents the normalized value of the i-th parameter, X i represents the value of the i-th state parameter, X i,min represents the minimum value of the i-th state parameter after preprocessing, X i,max represents the maximum value of the i-th state parameter after preprocessing.

[0062] The calculation formula of the discriminant index in step 4 is:

[0063]

[0064] Wherein, k represents the value of the calculated mud cake discriminant index, x1 represents the normalized cutter head speed, x2 represents the normalized cutter head torque, x3-x8 represents the normalized A-F group of oil cylinder advancing pressure. X9 represents the normalized average advancing speed, x 10 represents the normalized penetration, x 11 represents the normalized total advancing force, x 12 -x 17 represents the normalized 1-6# excavation bin pressure, x 18 -x 19 represents the normalized 1# and 2# working bin pressure.

[0065] The threshold in step 5 can be selected according to the calculation result of the discriminant index. The greater the selected threshold, the more serious the mud cake phenomenon when diagnosing mud cake. Generally, the threshold can be selected as about 5% of the maximum value of the calculated discriminant index.

[0066] By screening the running data collected by the shield machine, the corresponding discriminant index value is calculated by using the data of the working state, and on this basis, a suitable threshold value is set, so that the mud cake condition of the cutter head of the shield machine can be effectively diagnosed, and the driver can identify the occurrence of the mud cake as soon as possible, and the mud cake can be cleaned.

[0067] According to the adaptive multi-level decomposition full-face tunnel boring machine cutter head torque long-time prediction system provided by the application, the working state data of the shield machine is collected by 19 state parameters in the tunneling process, the data is preprocessed to eliminate extreme abnormal values, and the shield machine running parameter sequence for analysis is obtained, the preprocessed data is normalized by using the minimum-maximum method, the mud cake discriminant index value of each time after normalization is calculated by using a discriminant formula, and the threshold value is reasonably set according to the calculated discriminant index to estimate the mud cake occurrence time.

[0068] The state parameters selected in the module M1 include the cutter head rotating speed, the cutter head torque, the A group oil cylinder advancing pressure, the B group oil cylinder advancing pressure, the C group oil cylinder advancing pressure, the D group oil cylinder advancing pressure, the E group oil cylinder advancing pressure, the F group oil cylinder advancing pressure, the advancing speed average value, the penetration, the total advancing force, the excavation bin pressure 1#, the excavation bin pressure 2#, the excavation bin pressure 3#, the excavation bin pressure 4#, the excavation bin pressure 5#, the excavation bin pressure 6#, the working bin pressure 1# and the working bin pressure 2#, and the standard for judging that the shield machine is in the working state is that the cutter head rotating speed, the cutter head torque and the penetration are all not 0.

[0069] The module M2 includes that the extreme abnormal data is eliminated and five-point sliding average processing is performed by setting a threshold value, and the calculation formula is as follows:

[0070]

[0071] Wherein, T H,i is the upper threshold of the i th state parameter, T L,i is the lower threshold of the i th state parameter, Q 3,i and Q 1,i respectively represent the upper quartile and the lower quartile of the i th state parameter in the working state.

[0072] The module M3 includes that the preprocessed data is normalized, and the calculation formula is as follows:

[0073]

[0074] Wherein, x i represents the normalized value of the i th parameter, X i represents the value of the i th state parameter, and X i,minX represents the minimum value of the i-th state parameter after preprocessing. i,max This represents the maximum value of the i-th state parameter after preprocessing.

[0075] The formula for calculating the discrimination index in module M4 is as follows:

[0076]

[0077] Where, k represents the calculated sludge cake discrimination index, x1 represents the normalized cutterhead speed, x2 represents the normalized cutterhead torque, x3-x8 represent the normalized AF group cylinder propulsion pressure, and x9 represents the normalized average propulsion speed. 10 x represents the normalized penetration. 11 x represents the normalized total thrust. 12 -x 17 x represents the normalized pressure of excavation chambers 1#-6#. 18 -x 19 This represents the normalized pressure of working chambers #1 and #2.

[0078] The threshold setting in module M5 can be selected based on the calculation results of the discriminant index. The larger the selected threshold, the more severe the mud cake phenomenon will be when mud cake is diagnosed. Generally, the threshold can be selected as about 5% of the maximum value of the calculated discriminant index.

[0079] By filtering the operational data collected by the tunnel boring machine (TBM) and calculating the corresponding discrimination index based on its working status data, and setting an appropriate threshold, the condition of mud cake on the TBM cutterhead can be effectively diagnosed, helping the operator to identify the occurrence of mud cake as early as possible and clean it up.

[0080] Example 2:

[0081] Example 2 is a variation of Example 1.

[0082] refer to Figure 1 and Figure 2 This invention provides a method for diagnosing mud cake buildup on the cutterhead of a tunnel boring machine based on historical operating data, comprising the following steps:

[0083] Step 1: Select 19 state parameters during the actual tunneling process of the tunnel boring machine for evaluation and extract 7505 data points under working conditions;

[0084] Step 2: Preprocess the data to remove extreme outliers, resulting in 7446 sequences of tunnel boring machine operating parameters for analysis;

[0085] Step 3: Normalize the preprocessed data;

[0086] Step 4: Calculate the normalized cake discrimination index value of each time point by using the discriminant formula;

[0087] Step 5: According to the calculated discriminant index, set the threshold value to 0.65, and the data exceeding the threshold value is considered to have occurred cake;

[0088] From Figure 2 It can be seen that the proposed shield cutter cake diagnosis method based on historical operation data can accurately distinguish the data of two sections of cake, which shows that the proposed shield cutter cake diagnosis method based on historical operation data has good effect on cake diagnosis and is conducive to the discrimination of cake.

[0089] Those skilled in the art know that, in addition to implementing the system, device and each module thereof provided by the present application in the form of pure computer readable program code, the same program can also be realized by logically programming the method steps in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers and embedded microcontrollers. Therefore, the system, device and each module thereof provided by the present application can be considered as a hardware component, and the modules included therein for realizing various programs can also be considered as structures within the hardware component; the modules for realizing various functions can also be considered as both software programs for realizing methods and structures within the hardware component.

[0090] The specific embodiments of the present application are described above. It should be understood that the present application is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essential content of the present application. In the case of no conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A method for diagnosing a shield machine cutter cake based on historical operation data, characterized in that, The method comprises the following steps: Step 1: collecting state parameters in the tunneling process of the shield machine, and extracting working state data of the shield machine; Step 2: pre-processing the state data, eliminating data not meeting preset requirements, and obtaining a shield machine running parameter sequence for analysis; Step 3: normalizing the pre-processed data by using the minimum-maximum method; Step 4: calculating a mud cake discrimination index value of each time after normalization by using a discrimination formula; Step 5: setting a threshold according to the calculated discrimination index value, and estimating a mud cake occurrence time; The state parameters include a cutter head rotating speed, a cutter head torque, A group cylinder pushing pressure, B group cylinder pushing pressure, C group cylinder pushing pressure, D group cylinder pushing pressure, E group cylinder pushing pressure, F group cylinder pushing pressure, an average pushing speed, a penetration degree, a total pushing force, excavation chamber pressure 1#, excavation chamber pressure 2#, excavation chamber pressure 3#, excavation chamber pressure 4#, excavation chamber pressure 5#, excavation chamber pressure 6#, working chamber pressure 1# and working chamber pressure 2#, and the standard for judging that the shield machine is in a working state is that the cutter head rotating speed, the cutter head torque and the penetration degree are all not 0; The discrimination formula in Step 4 is: wherein k represents a value of the calculated caked mud discrimination index; x1 represents a normalized cutterhead rotational speed; x2 represents a normalized cutterhead torque; x3-x8 represent normalized individual cylinder thrust pressures; x9 represents a normalized average thrust speed; x 10 represents a normalized penetration; x 11 represents a normalized total thrust; x 12 -x 17 represents a normalized individual bin pressure; x 18 -x 19 represents a normalized individual working bin pressure; i is a serial number.

2. The method of claim 1, wherein, Step 1 comprises the following steps: Step 1.1: selecting the cutter head rotating speed, the cutter head torque, the cylinder pushing pressure of each group, the average pushing speed, the penetration degree, the total pushing force, the excavation chamber pressure and the working chamber pressure data as the state parameters of the shield machine; Step 1.2: selecting data in which the cutter head rotating speed, the cutter head torque and the penetration degree are all not 0 as the working state data of the shield machine.

3. The method of claim 1, wherein, Step 2 comprises the following steps: Step 2.1: taking an absolute value of the cutter head torque of the shield machine in the working state; Step 2.2: setting a threshold to eliminate data not meeting preset requirements, and the calculation formula of the threshold is: where T H,i is the upper threshold of the i-th state parameter; T L,i is the lower threshold of the i-th state parameter; Q 3,i and Q 1,i represent the upper quartile and the lower quartile of the i-th state parameter in the working state, respectively. Step 2.3: performing five-point sliding average processing on the eliminated data, thereby obtaining the shield machine running parameter sequence for analysis.

4. The method of claim 1, wherein, Step 5 comprises the following steps: selecting a threshold according to the calculation result of the discrimination index, taking 5% of the maximum value of the calculated discrimination index, if the threshold is set too high, it is determined that the mud cake condition is more serious when the mud cake occurs.

5. A shield machine cutter cake diagnosis system based on historical operation data, characterized in that, The method comprises the following steps: Module M1: collecting state parameters in the tunneling process of the shield machine, and extracting working state data of the shield machine; Module M2: pre-processing the state data, eliminating data not meeting preset requirements, and obtaining a shield machine running parameter sequence for analysis; Module M3: normalizing the pre-processed data by using the minimum-maximum method; Module M4: calculating a mud cake discrimination index value of each time after normalization by using a discrimination formula; Module M5: setting a threshold according to the calculated discrimination index value, and estimating a mud cake occurrence time; The state parameters include the cutterhead rotating speed, the cutterhead rotating torque, the A-group oil cylinder pushing pressure, the B-group oil cylinder pushing pressure, the C-group oil cylinder pushing pressure, the D-group oil cylinder pushing pressure, the E-group oil cylinder pushing pressure, the F-group oil cylinder pushing pressure, the average pushing speed, the penetration, the total pushing force, the excavation chamber pressure 1#, the excavation chamber pressure 2#, the excavation chamber pressure 3#, the excavation chamber pressure 4#, the excavation chamber pressure 5#, the excavation chamber pressure 6#, the working chamber pressure 1# and the working chamber pressure 2#, and the criterion for judging that the shield machine is in the working state is that the cutterhead rotating speed, the cutterhead rotating torque and the penetration are all not 0; The discriminant formula in the module M4 is: wherein k represents a value of the calculated caked soil discrimination index; x1 represents a normalized cutterhead rotation speed; x2 represents a normalized cutterhead torque; x3-x8 represent normalized cylinder advancing pressures of each group; x9 represents a normalized advancing speed average; x 10 represents a normalized penetration; x 11 represents a normalized total advancing force; x 12 -x 17 represents a normalized pressure of each excavation chamber; x 18 -x 19 represents a normalized pressure of each working chamber; i is a serial number.

6. The shield machine cutter balling-up diagnosis system based on historical operation data according to claim 5, characterized in that, The module M1 comprises: Module M1.1: selecting the cutterhead rotating speed, the cutterhead rotating torque, the oil cylinder pushing pressure of each group, the average pushing speed, the penetration, the total pushing force, the excavation chamber pressure and the working chamber pressure data as the state parameters of the shield machine; Module M1.2: selecting the data that the cutterhead rotating speed, the cutterhead rotating torque and the penetration are all not 0 as the working state data of the shield machine.

7. The shield machine cutter cake diagnosis system based on historical operation data according to claim 5, characterized in that, The module M2 comprises: Module M2.1: taking the absolute value of the cutterhead rotating torque of the shield machine in the working state; Module M2.2: setting a threshold value to eliminate the data that does not meet the preset requirement, and the calculation formula of the threshold value is: where T H,i is the upper threshold of the i-th state parameter; T L,i is the lower threshold of the i-th state parameter; Q 3,i and Q 1,i represent the upper quartile and the lower quartile of the i-th state parameter in the working state, respectively. Module M2.3: performing five-point sliding average processing on the eliminated data, so as to obtain the shield machine running parameter sequence for analysis.

8. The shield machine cutter cake diagnosis system based on historical operation data according to claim 5, characterized in that, The module M5 comprises: selecting a threshold value according to the calculation result of the discriminant index, taking 5% of the maximum value of the calculated discriminant index, if the threshold value is higher than the range, it is determined that the mud cake occurs, and if the threshold value is set higher, it is diagnosed that the mud cake condition is more serious when the mud cake occurs.

Images