Shield cutter change prediction method and system based on thrust torque change relationship

Abstract

The present invention provides a shield tool change prediction method and system based on the relationship between thrust and torque changes, and relates to the technical field of shield construction. The prediction method includes the following steps: collecting the original thrust data, original torque data, and original propulsion speed data of the target shield machine in a continuous time span; performing data processing and reconstruction on the original data to obtain reconstructed thrust data, reconstructed torque data, and reconstructed propulsion speed data; taking derivatives of the reconstructed data respectively to obtain the growth trend law of the data, and taking the product of the thrust data derivative, the torque data derivative, and the propulsion speed data derivative in pairs, and analyzing the product results. This method uses the slope change correlation and threshold judgment to comprehensively decide the tool change judgment, which is a supplement to the tool withdrawal detection and installation monitoring. At the same time, this method can be embedded in the on-site shield monitoring system by writing an integrated test.

Description

Technical Field

[0001] The present invention relates to the technical field of shield construction, and in particular to a shield cutter change prediction method and system based on a thrust torque variation relationship. Background Art

[0002] Shield machines are widely used as primary equipment in tunnel construction due to their high construction speed and minimal impact on the surrounding environment. Their performance and stability directly impact the progress and safety of the project. During the tunneling process, wear and damage to the cutters are common problems. Regular and timely cutter replacement is key to ensuring the continued efficiency of the shield machine. However, current cutter replacement methods rely primarily on empirical judgment or scheduled replacement, lacking scientific predictive methods. This leads to inaccurate cutter change timing, impacting construction efficiency and costs.

[0003] Currently, there are many methods for detecting roller cutter wear, such as directly monitoring the roller cutter wear through a roller cutter monitoring device. The advantage of this method is that it is relatively intuitive, but due to the complexity of the sensor's working environment, there is a certain judgment error; the wear monitoring method for shield scrapers is mainly through pre-embedded sensor devices in the scraper or odor method detection. When the scraper wear reaches a certain value, the sensor will detect the signal of the tool wear warning point (electromagnetic changes or odor, etc.). This method has a certain lag and requires a certain cost. Summary of the Invention

[0004] Purpose of the invention: In order to solve the problem that the detection of shield scraper wear mainly relies on the inconvenience of blade withdrawal detection, and the installation monitoring device needs to be worn to a certain position before the wear threshold alarm is triggered, the present invention proposes a shield blade change prediction method based on the relationship between thrust and torque changes, and proposes a system that can implement the above method. The blade change judgment is comprehensively decided through the correlation of slope changes and threshold judgment, which is a supplement to blade withdrawal detection and installation monitoring. At the same time, the method can be embedded in the on-site shield monitoring system by writing an integrated test.

[0005] To achieve the above object, the first aspect of the present invention provides a shield tool change prediction method based on the relationship between thrust and torque changes, the method comprising the following steps:

[0006] Collecting a tunneling construction data set of a target shield machine over a continuous time span; the tunneling construction data set includes original thrust data, original torque data, and original propulsion speed data;

[0007] Performing data processing and reconstruction on the tunneling construction data set to obtain a reconstructed data set; the reconstructed data set includes reconstructed thrust data, reconstructed torque data, and reconstructed propulsion speed data;

[0008] Derivatives are taken for the reconstructed thrust data, the reconstructed torque data, and the reconstructed propulsion speed data to obtain a thrust data derivative, a torque data derivative, and a propulsion speed data derivative;

[0009] The thrust data derivative, torque data derivative, and propulsion speed data derivative are quadratured in pairs, and the quadrature results are analyzed. 、 、 :

[0010] If the kth ring If it is negative, it is ready for tool change;

[0011] If the kth ring is positive, and the data of the last two rings continue to increase, that is, ,and If it is negative, it is determined that the tool needs to be changed; otherwise, the tool does not need to be changed and the process continues.

[0012] In a further embodiment of the first aspect, the original thrust data of the target shield machine under the continuous excavation k-ring timing is obtained by reading the data sensor of the target shield machine. , raw torque data , original propulsion speed data ;

[0013] in, , k represents the current excavation ring, and K represents the total number of excavation rings of the shield machine in a continuous time span.

[0014] In a further embodiment of the first aspect, performing data processing and reconstruction on the tunneling construction dataset to obtain a reconstructed dataset specifically includes:

[0015] The raw thrust data Reduce it by a predetermined ratio to match the original torque data , original propulsion speed data are of the same order of magnitude.

[0016] When the data sensor of the target shield machine is powered off, or the target shield machine itself is powered off, the complement processing is performed: starting from the data collected in the 2nd ring and ending with the last ring K collected; it is judged in turn whether the value is 0. If the sensor value of the kth ring is 0, the data of the k-1th ring is assigned to the kth ring.

[0017] In a further embodiment of the first aspect, when the target shield machine is in operation, mechanical vibration causes interference information in the signals collected by the data sensor. Therefore, the tunneling construction data set is filtered and denoised. A one-dimensional wavelet denoising function is used to filter and denoise the tunneling construction data set. The mathematical expression for calling the one-dimensional wavelet denoising function is as follows:

[0018]

[0019] Where XD is the processed signal; X is the signal before the processor; TPTR is the threshold selection rule; SORH specifies the threshold selection method; SCAL is the threshold scale change ratio; N is the number of wavelet decomposition layers; wname is the basic wavelet function;

[0020] Thrust data after filtering and noise reduction The expression is as follows:

[0021]

[0022] Torque data after filtering and noise reduction The expression is as follows:

[0023]

[0024] Propulsion speed data after filtering and noise reduction The expression is as follows:

[0025]

[0026] Where, 、 、 They represent the original thrust data, original torque data, and original propulsion speed data respectively; the threshold selection rule selects heursure, the threshold method selects soft threshold s, the threshold scale change ratio is one to represent the basic mode, the wavelet decomposition layer number is 3, and the basic wavelet function selects orthogonal wavelet sym8.

[0027] In a further embodiment of the first aspect, the specific process of filtering and denoising the tunneling construction data set is as follows: the signal collected by the data sensor is split into low-frequency information and high-frequency information, and the low-frequency information is combined and reconstructed. The mathematical expression is as follows:

[0028]

[0029]

[0030] Where a is the expansion factor and b is the translation factor; is the wavelet function constant; is the basic wavelet function; is the basic wavelet Fourier transform of ; k represents the current excavation ring; Indicates the excavation construction data of the kth ring; Represents the tunneling construction data after reconstruction and filtering;

[0031] Wavelet function constant The mathematical expression is as follows:

[0032]

[0033] The expression of the basic wavelet function is as follows:

[0034]

[0035] Where, k represents the current excavation ring; is the basic wavelet Fourier transform of is the unit function.

[0036] In a further embodiment of the first aspect, the reconstructed dataset Performing derivative processing, we can get the growth trend of the data, which is expressed as follows:

[0037]

[0038] Where, Represents the data set after differentiation; Indicates the number of rings for each excavation, and the value here is 1; represents the k-th ring excavation construction data after reconstruction and filtering; Represents the first The excavation construction data of the ring.

[0039] In a further embodiment of the first aspect, the derivatives of the thrust data, the derivatives of the torque data, and the derivatives of the propulsion speed data are quadratured pairwise, and the quadrature results are analyzed:

[0040]

[0041]

[0042]

[0043] in, is the thrust value after derivation; is the torque value after derivation; is the value of the propulsion speed after derivation;

[0044] Sequentially 、 、 Analyze the numerical results:

[0045] If the kth ring If it is negative, it is ready for tool change;

[0046] If the kth ring is positive, and the data of the last two rings continue to increase, that is, ,and If it is negative, it is determined that the tool needs to be changed; otherwise, the tool does not need to be changed and the process continues.

[0047] A second aspect of the present invention provides a shield tool change prediction system, comprising a data acquisition module, a first data processing module, a second data processing module, and an analysis module. The shield tool change prediction system automatically executes the shield tool change prediction method based on the thrust-torque relationship described in the first aspect.

[0048] The acquisition module is used to acquire a tunneling construction data set of a target shield machine in a continuous time span; the tunneling construction data set includes original thrust data, original torque data, and original propulsion speed data.

[0049] The first data processing module is used to perform data processing and reconstruction on the tunneling construction data set to obtain a reconstructed data set; the reconstructed data set includes reconstructed thrust data, reconstructed torque data, and reconstructed propulsion speed data.

[0050] The second data processing module is used to respectively derive the reconstructed thrust data, the reconstructed torque data, and the reconstructed propulsion speed data to obtain a thrust data derivative, a torque data derivative, and a propulsion speed data derivative.

[0051] The analysis module is used to calculate the product of the thrust data derivative, torque data derivative, and propulsion speed data derivative, and analyze the product results. 、 、 .

[0052] If the kth ring If it is negative, it is ready to change the tool; if the kth ring is positive, and the data of the last two rings continue to increase, that is, ,and If it is negative, it is determined that the tool needs to be changed; otherwise, the tool does not need to be changed and the process continues.

[0053] Beneficial effects: The shield cutter change prediction method based on the relationship between thrust and torque changes proposed in the present invention monitors the thrust and torque changes during the operation of the shield machine in real time, and through change correlation analysis, it issues an early warning of the timing of tool wear and tool change, thereby arranging tool change in advance to ensure construction efficiency and safety. This method integrates the correlation method for analysis and can be integrated into the shield data monitoring system, and this method can also be applied to shield cutters. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is an overall flow chart of the shield tool change prediction method based on the thrust torque change relationship in the embodiment.

[0055] Figure 2It is a logic diagram for analyzing tool change in the embodiment.

[0056] Figure 3 This is a flow chart of performing data processing and reconstruction on a tunneling construction data set in an embodiment.

[0057] Figure 4 Schematic diagram of the shield tool change prediction system in the embodiment. DETAILED DESCRIPTION

[0058] In the following description, numerous specific details are provided to provide a more thorough understanding of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced without one or more of these details. In other instances, certain technical features well known in the art have not been described to avoid confusion with the present invention.

[0059] To address the inconvenience of shield blade wear detection, which primarily relies on blade withdrawal detection, and the need for installed monitoring devices to trigger wear threshold alarms only after wear reaches a certain level, this embodiment proposes a shield blade change prediction method based on the relationship between thrust and torque changes. This method uses slope change correlation and threshold judgment to comprehensively determine blade changes, complementing blade withdrawal detection and installation monitoring. Furthermore, this method can be embedded in on-site shield monitoring systems through the development of integrated tests. The detailed process of this shield blade change prediction method is described below with reference to the accompanying figures.

[0060] See Figure 1 This embodiment discloses a shield tool change prediction method based on the relationship between thrust and torque changes, and the steps are as follows:

[0061] Step 1: Use the thrust, torque, and propulsion speed sensors of the shield machine to collect relevant data and display the read data y(k) through the shield monitoring system. For thrust, is the torque, is the propulsion speed, k is the time series, the unit is second (s);

[0062] The thrust value is reduced by 10,000 times to be on the same order of magnitude as the torque and speed displays, which facilitates data display. Due to occasional phenomena such as power outages of the data sensor and the shield machine, the shield machine excavation parameters read by the sensor will be 0, which will cause a large deviation in the subsequent tool change prediction, and the synchronously collected data needs to be "complemented". At the same time, due to the complexity of the sensor's working environment, the "noise" signals generated by factors such as vibration need to be filtered and denoised.

[0063] The complement processing method is: starting from the data collected by the kth ring (k≥2), and ending with the last ring N collected; successively determine whether the value is 0. If the sensor value of the kth ring is 0, then assign the data of the k-1th ring to the kth ring;

[0064] The process of data denoising is shown in Figure 2 The shield machine excavation parameters collected by the sensor may contain interference information due to mechanical vibration, data analysis errors, etc. Therefore, data denoising, that is, filtering, is required. The principle is to split the low-frequency signal and high-frequency information, reconstruct the low-frequency information, and calculate the formula after reconstruction and filtering:

[0065] , where a is the scaling factor (greater than 0) and b is the translation factor (can be positive or negative). , is the wavelet function constant, and the expression is , is the basic wavelet Fourier transform of Haar, Daubechies, Symlets, etc. can be selected. In this method, the sym8 function in Symlets is selected, and its mathematical expression is:

[0066] , u(k) is the unit function.

[0067] Step 2: Derivative the processed data to obtain the growth trend of the data. The specific method is:

[0068]

[0069] In this method, The value is 1.

[0070] Step 3: Take the derivatives of thrust, torque, and propulsion speed and calculate the product of them, that is, is the thrust value after derivation, is the torque value after derivation, is the value of the propulsion speed after derivation.

[0071]

[0072]

[0073]

[0074] Step 4: According to the product result, 、 、 The numerical results are analyzed in Figure 2 :

[0075] If the kth ring If it is negative, it is ready to change the tool; if the kth ring is positive, and the data of the last two rings continue to increase, that is, ,and If it is negative, it can be determined that the tool needs to be changed; otherwise, the tool does not need to be changed and the process continues.

[0076] The embodiment of the present invention also discloses a shield tool change prediction system 500, see Figure 4 . The shield tool change prediction system 500 includes four components: an acquisition module 501, a first data processing module 502, a second data processing module 503, and an analysis module 504. The acquisition module 501 is used to collect the tunneling construction data set of the target shield machine under a continuous time span; the tunneling construction data set includes original thrust data, original torque data, and original propulsion speed data. The first data processing module 502 is used to perform data processing and reconstruction on the tunneling construction data set to obtain a reconstructed data set; the reconstructed data set includes reconstructed thrust data, reconstructed torque data, and reconstructed propulsion speed data. The second data processing module 503 is used to respectively derive the reconstructed thrust data, reconstructed torque data, and reconstructed propulsion speed data to obtain thrust data derivatives, torque data derivatives, and propulsion speed data derivatives. The analysis module 504 is used to take the product of the thrust data derivatives, torque data derivatives, and propulsion speed data derivatives in pairs, and analyze the product results. 、 、 If the kth ring If it is negative, it is ready to change the tool; if the kth ring is positive, and the data of the last two rings continue to increase, that is, ,and If it is negative, it is determined that the tool needs to be changed; otherwise, the tool does not need to be changed and the tool continues to be advanced. The shield tool change prediction system 500 can automatically execute the shield tool change prediction method based on the thrust torque change relationship disclosed in the above embodiment, which will not be described in detail here.

[0077] Furthermore, the shield tool change prediction method based on the relationship between thrust and torque changes disclosed in the above embodiment can be embedded in an on-site shield monitoring system by being written as executable code. The executable code runs in the on-site shield monitoring system in the form of software, and the software can be written to a computer-readable storage medium. More specific examples of the computer-readable storage medium in this embodiment may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0078] Computer-readable storage media may include a data signal transmitted in baseband or as part of a carrier wave, which carries readable program code. Such a transmitted data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0079] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A shield tool change prediction method based on the relationship between thrust and torque changes, characterized in that: The steps include: Collecting a tunneling construction data set of a target shield machine in a continuous time span; the tunneling construction data set includes original thrust data, original torque data, and original propulsion speed data; Performing data processing and reconstruction on the excavation construction data set to obtain a reconstructed data set; the reconstructed data set includes reconstructed thrust data, reconstructed torque data, and reconstructed propulsion speed data; Deriving the reconstructed thrust data, the reconstructed torque data, and the reconstructed propulsion speed data respectively to obtain a thrust data derivative, a torque data derivative, and a propulsion speed data derivative; The derivatives of the thrust data, the derivatives of the torque data, and the derivatives of the propulsion speed data are multiplied in pairs: ； ； ； in, is the derivative of thrust data; is the derivative of torque data; is the derivative of propulsion velocity data; Analyze the quadrature results , , : If the kth ring If it is negative, it is ready for tool change; If the kth ring is positive, and the data of the last two rings continue to increase, that is, ,and If it is negative, it is determined that the tool needs to be changed; otherwise, the tool does not need to be changed and the process continues.

2. The shield tool change prediction method based on thrust torque change relationship according to claim 1 is characterized in that: By reading the data sensor of the target shield machine, the original thrust data of the target shield machine under the continuous excavation k-ring timing is obtained. , Raw torque data , original propulsion speed data ; in, , k represents the current excavation ring, and K represents the total number of excavation rings of the shield machine in a continuous time span.

3. The shield tool change prediction method based on thrust torque change relationship according to claim 2 is characterized in that: Performing data processing and reconstruction on the excavation construction data set to obtain a reconstructed data set specifically includes: The raw thrust data Reduce it by a predetermined ratio to match the original torque data , original propulsion speed data are of the same order of magnitude.

4. The shield tool change prediction method based on thrust torque change relationship according to claim 3 is characterized in that: Performing data processing and reconstruction on the excavation construction data set to obtain a reconstructed data set also includes: When the data sensor of the target shield machine is powered off, or the target shield machine itself is powered off, the complement processing is performed, including: Starting from the data collected in the 2nd ring and ending with the last ring K, determine whether the value is 0 in turn. If the sensor value of the kth ring is 0, assign the data of the k-1th ring to the kth ring.

5. The shield tool change prediction method based on thrust torque change relationship according to claim 3 is characterized in that: Performing data processing and reconstruction on the excavation construction data set to obtain a reconstructed data set also includes: using a one-dimensional wavelet denoising function to filter and reduce noise on the excavation construction data set; the calling mathematical expression of the one-dimensional wavelet denoising function is as follows: ； Where XD is the processed signal; X is the signal before the processor; TPTR is the threshold selection rule; SORH specifies the threshold selection method; SCAL is the threshold scale change ratio; N is the number of wavelet decomposition layers; wname is the basic wavelet function; Thrust data after filtering and noise reduction The expression is as follows: ； Torque data after filtering and noise reduction The expression is as follows: ； Propulsion speed data after filtering and noise reduction The expression is as follows: ； In the formula, , , They represent the original thrust data, original torque data, and original propulsion speed data respectively; the threshold selection rule selects heursure, the threshold method selects the soft threshold s, the threshold scale change ratio is one represents the basic mode, the wavelet decomposition layer number is 3, and the basic wavelet function selects the orthogonal wavelet sym8.

6. The shield tool change prediction method based on thrust torque change relationship according to claim 5 is characterized in that: Performing data processing and reconstruction on the excavation construction data set to obtain a reconstructed data set also includes: The signal collected by the data sensor is split into low-frequency information and high-frequency information, and the low-frequency information is combined and reconstructed. The mathematical expression is as follows: ； ； In the formula, a is the expansion factor and b is the translation factor; is the wavelet function constant; is the basic wavelet function; k represents the current excavation ring; Indicates the excavation construction data of the kth ring; Represents the excavation construction data after reconstruction filtering.

7. The shield tool change prediction method based on thrust torque change relationship according to claim 6 is characterized in that: Wavelet function constant The mathematical expression is as follows: ； The expression of the basic wavelet function is as follows: ； In the formula, is a unit function; k represents the current excavation ring; The basic wavelet The Fourier transform of .

8. The shield tool change prediction method based on the thrust torque change relationship according to claim 7 is characterized in that: Reconstructing the dataset By performing derivation processing, we can obtain the growth trend of the data, which is expressed as follows: ； In the formula, represents the data set after derivation; Indicates the number of rings for each excavation, and the value here is 1; represents the k-th ring excavation construction data after reconstruction and filtering; Represents the reconstruction filter after The excavation construction data of the ring.

9. A shield tool change prediction system, characterized in that: include: A collection module is used to collect a tunneling construction data set of a target shield machine in a continuous time span; the tunneling construction data set includes original thrust data, original torque data, and original propulsion speed data; A first data processing module is used to perform data processing and reconstruction on the tunneling construction data set to obtain a reconstructed data set; the reconstructed data set includes reconstructed thrust data, reconstructed torque data, and reconstructed propulsion speed data; A second data processing module is used to respectively derive the reconstructed thrust data, the reconstructed torque data, and the reconstructed propulsion speed data to obtain a thrust data derivative, a torque data derivative, and a propulsion speed data derivative; An analysis module is used to calculate the product of the thrust data derivative, the torque data derivative, and the propulsion speed data derivative, and analyze the product results. , , : If the kth ring If it is negative, it is ready for tool change; If the kth ring is positive, and the data of the last two rings continue to increase, that is, ,and If it is negative, it is determined that the tool needs to be changed; otherwise, it does not need to be changed and the tool continues to be advanced; The shield tool change prediction system can automatically execute the shield tool change prediction method based on the thrust torque change relationship as described in any one of claims 1 to 8.

Images