Shield cutter wear prediction method, device, electronic equipment and product

Abstract

The application discloses a shield cutter wear prediction method and device, electronic equipment and product, and relates to the technical field of shield cutter wear prediction. The wear data, tunneling parameters and geological condition parameters of the shield cutter are acquired; based on the wear data, tunneling parameters, stratum type and stratum parameters, a wear rate model of the shield cutter in the current stratum and a multi-dimensional wear amount curve of the shield cutter are established; from a historical database, a plurality of groups of multi-dimensional historical wear amount curves of the shield cutter in the current stratum with the highest similarity to the multi-dimensional wear amount curve and higher than a preset threshold are acquired; based on the sampling data in the plurality of groups of multi-dimensional historical wear amount curves, the model parameters of the wear rate model of the shield cutter in the current stratum are optimized, the optimized wear rate model of the shield cutter in the current stratum is obtained, and the wear amount of the shield cutter is predicted. The application can accurately predict the wear amount of the shield cutter, and helps project managers to more scientifically formulate construction schemes.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of shield cutter wear prediction, and particularly relates to a shield cutter wear prediction method and device, an electronic device and a product. BACKGROUND

[0002] As the core equipment of tunnel engineering, a shield machine (TBM) has its cutter directly contact with a rock-soil layer, bears high stress, high temperature and complex friction, and is a key component for determining the tunneling efficiency and cost. However, cutter wear is one of the most prominent engineering problems in shield construction.

[0003] The mechanism of cutter wear is complex and is affected by multiple factors such as geological conditions and construction parameters. Traditional cutter wear monitoring mainly collects cutter working state data (such as vibration amplitude mutation and temperature abnormal rise) in real time through vibration, temperature and torque sensors installed on the cutter head or cutter, infers the wear degree, and some high-end devices also have image recognition cutter wear function. However, the existing cutter wear monitoring can only reflect the current wear state of the shield cutter, and cannot predict the wear amount of the shield cutter, which often leads to the inability to reasonably customize the construction scheme according to the wear amount prediction data of the shield cutter, thereby increasing the construction cost.

[0004] Therefore, how to provide an effective scheme to accurately predict the wear amount of the shield cutter so as to scientifically and reasonably customize the construction scheme and reduce the construction cost has become a difficult problem to be solved in the prior art. SUMMARY

[0005] The application aims to provide a shield cutter wear prediction method, device, electronic device and product to solve the above problems in the prior art.

[0006] In order to achieve the above-mentioned purpose, the application adopts the following technical scheme:

[0007] In a first aspect, the application provides a shield cutter wear prediction method, comprising:

[0008] obtaining wear data, tunneling parameters and geological condition parameters of the shield cutter in the tunneling process in real time, wherein the geological condition parameters include stratum type and stratum parameters;

[0009] establishing a wear rate model of the shield cutter in the current stratum and a multi-dimensional wear amount curve of the shield cutter in the current stratum based on the wear data, tunneling parameters, stratum type and stratum parameters obtained in the current period, wherein the multi-dimensional wear amount curve of the shield cutter in the current stratum includes wear amount curves of the shield cutter in multiple different dimensions in the current stratum;

[0010] Obtain multiple sets of multi-dimensional historical wear curves of the shield cutter in the current stratum from the historical database, which have the highest similarity to the multi-dimensional wear curve and are higher than a preset threshold.

[0011] Based on the sampled data from the multiple sets of multi-dimensional historical wear curves, the model parameters of the wear rate model of the shield cutter in the current stratum are optimized to obtain the optimized wear rate model of the shield cutter in the current stratum.

[0012] Based on the optimized wear rate model of the tunnel boring machine cutter in the current stratum, the wear amount of the tunnel boring machine cutter is predicted.

[0013] Based on the above-disclosed content, this invention acquires in real-time wear data, tunneling parameters, and geological condition parameters of the tunnel boring machine (TBM) cutter during the tunneling process. The geological condition parameters include stratum type and stratum parameters. Based on the wear data, tunneling parameters, stratum type, and stratum parameters acquired in the current time period, a wear rate model of the TBM cutter in the current stratum and a multi-dimensional wear curve of the TBM cutter in the current stratum are established. The multi-dimensional wear curve of the TBM cutter in the current stratum includes wear curves of the TBM cutter in multiple different dimensions within the current stratum. Multiple sets of multi-dimensional historical wear curves of the TBM cutter in the current stratum are obtained from a historical database, with the highest similarity to the multi-dimensional wear curves and a similarity exceeding a preset threshold. Based on the sampled data from these multiple sets of multi-dimensional historical wear curves, the model parameters of the wear rate model of the TBM cutter in the current stratum are optimized to obtain an optimized wear rate model of the TBM cutter in the current stratum. Based on the optimized wear rate model of the TBM cutter in the current stratum, the wear amount of the TBM cutter is predicted. In this way, the established wear rate model can be optimized by combining similar historical data. This allows for accurate prediction of the wear of tunnel boring machine cutters when using the wear rate model, which helps project managers to develop construction plans more scientifically, optimize resource allocation, reduce construction costs, and maximize economic benefits.

[0014] In one possible design, the tunneling parameters include shield cutter torque, shield cutterhead rotation speed and / or shield cutter thrust, and the formation parameters include rock hardness, sand content and / or water content;

[0015] The multi-dimensional wear curves of the shield cutter in the current stratum include the wear curve of the shield cutter in the current stratum as a function of propulsion speed, the wear curve as a function of shield cutter torque, the wear curve as a function of shield cutterhead rotation speed, the wear curve as a function of shield cutter thrust, the wear curve as a function of rock hardness, the wear curve as a function of sand content, and / or the wear curve as a function of water content.

[0016] In one possible design, the tunneling parameters include shield cutter torque, shield cutterhead rotation speed, and shield cutter thrust; the formation parameters include rock hardness and sand content; and the shield cutter wear rate model in the current formation is as follows: Where k represents an empirical constant, S represents rock hardness, S represents sand content, F represents shield cutter thrust, T represents shield cutter torque, and N represents shield cutterhead rotation speed. , , , and All of these represent model parameters.

[0017] In one possible design, The value range is 0.8-1.2. The value range is 0.5-1. The value range is 0.4-0.8. The value range is 0.3-0.7. The value range is 0.2-0.6.

[0018] In one possible design, multiple sets of multi-dimensional historical wear curves of the tunnel boring machine cutter in the current stratum are obtained from the historical database, showing the highest similarity to the multi-dimensional wear curve and with a similarity exceeding a preset threshold. These include:

[0019] The KNN algorithm is used to cluster the multidimensional wear curve with all multidimensional historical wear curves in the current stratum in the historical database to obtain multiple clusters.

[0020] Calculate the similarity between other multi-dimensional historical wear curves belonging to the same cluster as the multi-dimensional wear curve and the multi-dimensional wear curve;

[0021] Select multiple sets of multi-dimensional historical wear curves that have the highest similarity to the multi-dimensional wear curve and whose similarity is higher than a preset threshold.

[0022] In one possible design, the wear rate model of the tunnel boring machine cutter in the current stratum is a long short-term memory network model.

[0023] In one possible design, after predicting the wear of the tunnel boring machine (TBM) cutters based on a wear rate model optimized for the current geological formation, the method further includes:

[0024] Based on the wear prediction results of the tunnel boring machine cutter, the predicted remaining service life of the tunnel boring machine cutter is determined.

[0025] The system visualizes the predicted wear of tunnel boring machine (TBM) cutters and their predicted remaining service life.

[0026] Secondly, the present invention provides a shield tunneling cutter wear prediction device, comprising:

[0027] The first acquisition unit is used to acquire in real time the wear data, tunneling parameters and geological condition parameters of the shield cutter during the tunneling process. The geological condition parameters include stratum type and stratum parameters.

[0028] The establishment unit is used to establish a wear rate model of the shield cutter in the current stratum and a multi-dimensional wear curve of the shield cutter in the current stratum based on the wear data, tunneling parameters, stratum type and stratum parameters obtained in the current time period. The multi-dimensional wear curve of the shield cutter in the current stratum includes wear curves of the shield cutter in multiple different dimensions in the current stratum.

[0029] The second acquisition unit is used to acquire from the historical database multiple sets of multi-dimensional historical wear curves of the shield cutter in the current stratum that have the highest similarity to the multi-dimensional wear curve and the similarity is higher than a preset threshold.

[0030] The optimization unit is used to optimize the model parameters of the shield cutter wear rate model in the current stratum based on the sampled data in the multiple sets of multi-dimensional historical wear curves, so as to obtain the optimized wear rate model of the shield cutter in the current stratum.

[0031] The prediction unit is used to predict the wear of the tunnel boring machine cutter based on the optimized wear rate model of the cutter in the current stratum.

[0032] Thirdly, the present invention provides an electronic device comprising a memory, a processor, and a transceiver connected in sequence and communication, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the shield cutter wear prediction method as described in the first aspect or any possible design of the first aspect.

[0033] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, perform the shield cutter wear prediction method described in the first aspect or any possible design of the first aspect.

[0034] Fifthly, the present invention provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the shield cutter wear prediction method as described in the first aspect or any possible design of the first aspect.

[0035] Beneficial effects:

[0036] The shield tunneling cutter wear prediction method, device, electronic equipment, and product provided by this invention can optimize the established wear rate model by combining similar historical data. Thus, when predicting the wear amount of shield tunneling cutters through the wear rate model, the wear amount of shield tunneling cutters can be accurately predicted. This helps project managers to formulate construction plans more scientifically, optimize resource allocation, reduce construction costs, and maximize economic benefits. Attached Figure Description

[0037] Figure 1 A flowchart of the shield tunneling cutter wear prediction method provided in the embodiments of this application;

[0038] Figure 2 A schematic block diagram illustrating shield cutter wear prediction provided in an embodiment of this application;

[0039] Figure 3 This is a block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0041] It should be understood that although the terms first, second, etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, without departing from the scope of the exemplary embodiments of the invention.

[0042] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist simultaneously. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0043] To accurately predict the wear of tunnel boring machine (TBM) cutters, this application provides a method, device, electronic device, and product for predicting TBM cutter wear. This method, device, electronic device, and product can accurately predict the wear of TBM cutters, helping project managers to develop more scientific construction plans and reduce construction costs.

[0044] The shield cutter wear prediction method provided in this application can be applied to shield machine control systems or remote data monitoring platforms for remote monitoring of shield machines. It is understood that the execution entity described does not constitute a limitation on the embodiments of this application.

[0045] like Figure 1 The diagram shown is a flowchart of the shield cutter wear prediction method provided in the first aspect of this embodiment. The shield cutter wear prediction method may include, but is not limited to, the following steps S101 to S105.

[0046] Step S101. Real-time acquisition of wear data, tunneling parameters, and geological condition parameters of the shield cutter during the tunneling process.

[0047] In this embodiment of the application, the cutterhead monitoring system equipped in the shield machine control system acquires wear data and tunneling parameters of the shield cutter during the tunneling process. Geological condition parameters can be obtained through geological exploration before construction or through inversion by the shield machine's built-in sensors. The geological condition parameters include stratum type and stratum parameters.

[0048] Wear data of tunnel boring machine (TBM) cutters during the tunneling process can refer to the wear rate of the TBM cutters. Tunneling parameters may include, but are not limited to, TBM cutter torque, TBM cutterhead rotation speed, and / or TBM thrust. Formation parameters may include, but are not limited to, rock hardness, sand content, and / or water content.

[0049] In one or more embodiments, the acquired data may also include the type of shield cutter (such as a rolling cutter or a scraper) and the installation position of the cutter (such as the center or the edge).

[0050] In one or more embodiments, after obtaining wear data, tunneling parameters and geological condition parameters, the obtained data is also preprocessed, such as data alignment, missing value interpolation, outlier removal and data standardization.

[0051] Step S102. Based on the wear data, tunneling parameters, stratum type and stratum parameters obtained in the current time period, establish a wear rate model of the shield cutter in the current stratum, as well as a multi-dimensional wear curve of the shield cutter in the current stratum.

[0052] The wear rate model of the tunnel boring machine (TBM) cutter in the current stratum can be a semi-empirical model or a long short-term memory (LSTM) network model, etc. In this embodiment, the wear rate model of the TBM cutter in the current stratum adopts a semi-empirical model, which can be expressed as follows: Where k represents an empirical constant, S represents rock hardness, S represents sand content, F represents shield cutter thrust, T represents shield cutter torque, and N represents shield cutterhead rotation speed. , , , and All of these represent model parameters. The value range is generally 0.8-1.2. The value range is generally 0.5-1. The value range is generally 0.4-0.8. The value range is generally 0.3-0.7. The value range is generally 0.2-0.6.

[0053] The multi-dimensional wear curve of the tunnel boring machine (TBM) cutterhead in the current stratum includes wear curves of the TBM cutterhead in multiple different dimensions of the current stratum. Tunneling parameters include TBM cutterhead torque, TBM cutterhead rotation speed, and / or TBM cutterhead thrust; stratum parameters include rock hardness, sand content, and / or water content. Therefore, the multi-dimensional wear curve of the TBM cutterhead in the current stratum can include wear curves of the TBM cutterhead varying with advance speed, wear curves varying with TBM cutterhead torque, wear curves varying with TBM cutterhead rotation speed, wear curves varying with TBM cutterhead thrust, wear curves varying with rock hardness, wear curves varying with sand content, and / or wear curves varying with water content.

[0054] Step S103. Obtain multiple sets of multi-dimensional historical wear curves of the shield cutter in the current stratum from the historical database, which have the highest similarity to the multi-dimensional wear curve and the similarity is higher than the preset threshold.

[0055] Specifically, a clustering algorithm can be used to cluster the multi-dimensional wear curve with all historical multi-dimensional wear curves in the current stratum in the historical database, resulting in multiple clusters. Then, the similarity between the multi-dimensional wear curve and other historical multi-dimensional wear curves belonging to the same cluster is calculated. Finally, the groups of multi-dimensional historical wear curves with the highest similarity and a similarity higher than a preset threshold are selected.

[0056] The clustering algorithm can be, but is not limited to, the K-Nearest Neighbors (KNN) algorithm or the K-Means clustering algorithm. When calculating the similarity between the multi-dimensional wear curve and other multi-dimensional historical wear curves in the same cluster, the similarity between each dimension of the multi-dimensional wear curve and its corresponding historical multi-dimensional wear curve can be calculated. Then, a weighted average is used to obtain the similarity between the multi-dimensional wear curve and other multi-dimensional historical wear curves in the same cluster.

[0057] Step S104. Based on the sampling data in multiple sets of multi-dimensional historical wear curves, optimize the model parameters of the wear rate model of the shield cutter in the current stratum to obtain the optimized wear rate model of the shield cutter in the current stratum.

[0058] In this embodiment of the application, multiple sets of multi-dimensional historical wear curves can be sampled to obtain sampled data. The sampled data can be substituted into the wear rate model of the current stratum to optimize the model parameters of the wear rate model of the current stratum, thereby obtaining the optimized wear rate model of the shield cutter in the current stratum.

[0059] Step S105. Based on the optimized wear rate model of the shield cutter in the current stratum, predict the wear amount of the shield cutter.

[0060] Specifically, the wear of the tunnel boring machine (TBM) cutters can be predicted based on the optimized wear rate model of the cutters in the current geological formation, as well as the current wear data, tunneling parameters, and geological condition parameters of the cutters.

[0061] In one or more embodiments, after predicting the wear amount of the shield cutter based on the wear rate model optimized for the current stratum, the predicted remaining service life of the shield cutter can be determined based on the wear amount prediction results, and the wear amount prediction results and the predicted remaining service life of the shield cutter can be visualized.

[0062] The shield tunneling cutter wear prediction method provided by this invention acquires wear data, tunneling parameters, and geological condition parameters of the shield tunneling cutter during the tunneling process in real time. The geological condition parameters include stratum type and stratum parameters. Based on the wear data, tunneling parameters, stratum type, and stratum parameters acquired in the current time period, a wear rate model of the shield tunneling cutter in the current stratum and a multi-dimensional wear curve of the shield tunneling cutter in the current stratum are established. The multi-dimensional wear curve of the shield tunneling cutter in the current stratum includes wear curves of the shield tunneling cutter in multiple different dimensions in the current stratum. Multiple sets of multi-dimensional historical wear curves of the shield tunneling cutter in the current stratum with the highest similarity to the multi-dimensional wear curves and a similarity higher than a preset threshold are obtained from a historical database. Based on the sampled data in the multiple sets of multi-dimensional historical wear curves, the model parameters of the wear rate model of the shield tunneling cutter in the current stratum are optimized to obtain an optimized wear rate model of the shield tunneling cutter in the current stratum. Based on the optimized wear rate model of the shield tunneling cutter in the current stratum, the wear amount of the shield tunneling cutter is predicted. In this way, the established wear rate model can be optimized by combining similar historical data. This allows for accurate prediction of the wear of tunnel boring machine cutters when using the wear rate model. This helps project managers to develop construction plans more scientifically, optimize resource allocation, reduce construction costs, maximize economic benefits, and facilitates practical application and promotion.

[0063] Please see Figure 2 The second aspect of this application provides a shield tunneling cutter wear prediction device, which includes:

[0064] The first acquisition unit is used to acquire in real time the wear data, tunneling parameters and geological condition parameters of the shield cutter during the tunneling process. The geological condition parameters include stratum type and stratum parameters.

[0065] The establishment unit is used to establish a wear rate model of the shield cutter in the current stratum and a multi-dimensional wear curve of the shield cutter in the current stratum based on the wear data, tunneling parameters, stratum type and stratum parameters obtained in the current time period. The multi-dimensional wear curve of the shield cutter in the current stratum includes wear curves of the shield cutter in multiple different dimensions in the current stratum.

[0066] The second acquisition unit is used to acquire from the historical database multiple sets of multi-dimensional historical wear curves of the shield cutter in the current stratum that have the highest similarity to the multi-dimensional wear curve and the similarity is higher than a preset threshold.

[0067] The optimization unit is used to optimize the model parameters of the shield cutter wear rate model in the current stratum based on the sampled data in the multiple sets of multi-dimensional historical wear curves, so as to obtain the optimized wear rate model of the shield cutter in the current stratum.

[0068] The prediction unit is used to predict the wear of the tunnel boring machine cutter based on the optimized wear rate model of the cutter in the current stratum.

[0069] The working process, working details and technical effects of the shield cutter wear prediction device provided in the second aspect of this embodiment can be found in the first aspect of the embodiment, and will not be repeated here.

[0070] like Figure 3 As shown, a third aspect of this application provides an electronic device, including a memory, a processor, and a transceiver that are sequentially and communicatively connected. The memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the shield cutter wear prediction method as described in the first aspect of the application.

[0071] Specifically, the memory may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or last-in-first-out (FILO) memory, etc.; the processor may not be limited to microprocessors of the STM32F105 series, ARM (Advanced RISC Machines), x86 architecture processors, or processors with integrated NPU (neural-network processing units); the transceiver may be, but is not limited to, WiFi (Wireless Fidelity) wireless transceivers, Bluetooth wireless transceivers, General Packet Radio Service (GPRS) wireless transceivers, ZigBee (a low-power LAN protocol based on the IEEE 802.15.4 standard), 3G transceivers, 4G transceivers, and / or 5G transceivers, etc.

[0072] This fourth aspect of the embodiment provides a computer-readable storage medium storing instructions containing the shield cutter wear prediction method described in the first aspect of the embodiment. Specifically, the computer-readable storage medium stores instructions that, when executed on a computer, perform the shield cutter wear prediction method as described in the first aspect. The computer-readable storage medium refers to a data storage medium, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0073] The fifth aspect of this embodiment provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the shield cutter wear prediction method as described in the first aspect of the embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0074] It should be understood that specific details are provided in the following description to facilitate a complete understanding of the exemplary embodiments. However, those skilled in the art will understand that the exemplary embodiments can be implemented without these specific details. For example, the system may be shown in block diagrams to avoid obscuring the example with unnecessary details. In other instances, well-known processes, structures, and techniques may be shown without unnecessary details to avoid obscuring the exemplary embodiments.

[0075] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for predicting shield tunneling cutter wear, characterized in that, include: Real-time acquisition of wear data, tunneling parameters, and geological condition parameters of the tunnel boring machine cutter during the tunneling process, including stratum type and stratum parameters; Based on the wear data, tunneling parameters, stratum type and stratum parameters obtained in the current time period, a wear rate model of the shield cutter in the current stratum and a multi-dimensional wear curve of the shield cutter in the current stratum are established. The multi-dimensional wear curve of the shield cutter in the current stratum includes wear curves of the shield cutter in multiple different dimensions in the current stratum. Obtain multiple sets of multi-dimensional historical wear curves of the shield cutter in the current stratum from the historical database, which have the highest similarity to the multi-dimensional wear curve and are higher than a preset threshold. Based on the sampled data from the multiple sets of multi-dimensional historical wear curves, the model parameters of the wear rate model of the shield cutter in the current stratum are optimized to obtain the optimized wear rate model of the shield cutter in the current stratum. Based on the optimized wear rate model of the tunnel boring machine cutter in the current stratum, the wear amount of the tunnel boring machine cutter is predicted.

2. The shield tunneling cutter wear prediction method according to claim 1, characterized in that, The tunneling parameters include shield cutter torque, shield cutter head rotation speed and / or shield cutter thrust, and the formation parameters include rock hardness, sand content and / or water content; The multi-dimensional wear curves of the shield cutter in the current stratum include the wear curve of the shield cutter in the current stratum as a function of propulsion speed, the wear curve as a function of shield cutter torque, the wear curve as a function of shield cutterhead rotation speed, the wear curve as a function of shield cutter thrust, the wear curve as a function of rock hardness, the wear curve as a function of sand content, and / or the wear curve as a function of water content.

3. The shield tunneling cutter wear prediction method according to claim 2, characterized in that, The tunneling parameters include shield cutter torque, shield cutterhead rotation speed, and shield cutter thrust. The formation parameters include rock hardness and sand content. The shield cutter wear rate model in the current formation is as follows: Where k represents an empirical constant, S represents rock hardness, S represents sand content, F represents shield cutter thrust, T represents shield cutter torque, and N represents shield cutterhead rotation speed. , , , and All of these represent model parameters.

4. The shield tunneling cutter wear prediction method according to claim 3, characterized in that, The value range is 0.8-1.

2. The value range is 0.5-1. The value range is 0.4-0.

8. The value range is 0.3-0.

7. The value range is 0.2-0.

6.

5. The shield tunneling cutter wear prediction method according to claim 1, characterized in that, The system retrieves multiple sets of multi-dimensional historical wear curves of the tunnel boring machine cutter in the current stratum from the historical database. These curves have the highest similarity to the multi-dimensional wear curve and the similarity exceeds a preset threshold. The KNN algorithm is used to cluster the multidimensional wear curve with all multidimensional historical wear curves in the current stratum in the historical database to obtain multiple clusters. Calculate the similarity between other multi-dimensional historical wear curves belonging to the same cluster as the multi-dimensional wear curve and the multi-dimensional wear curve; Select multiple sets of multi-dimensional historical wear curves that have the highest similarity to the multi-dimensional wear curve and whose similarity is higher than a preset threshold.

6. The shield tunneling cutter wear prediction method according to claim 1, characterized in that, The wear rate model of the tunnel boring machine cutter in the current stratum is a long short-term memory network model.

7. The shield tunneling cutter wear prediction method according to claim 1, characterized in that, After predicting the wear of the tunnel boring machine (TBM) cutters based on an optimized wear rate model for the current geological formation, the method further includes: Based on the wear prediction results of the tunnel boring machine cutter, the predicted remaining service life of the tunnel boring machine cutter is determined. The system visualizes the predicted wear of tunnel boring machine (TBM) cutters and their predicted remaining service life.

8. A shield tunneling cutter wear prediction device, characterized in that, include: The first acquisition unit is used to acquire in real time the wear data, tunneling parameters and geological condition parameters of the shield cutter during the tunneling process. The geological condition parameters include stratum type and stratum parameters. The establishment unit is used to establish a wear rate model of the shield cutter in the current stratum and a multi-dimensional wear curve of the shield cutter in the current stratum based on the wear data, tunneling parameters, stratum type and stratum parameters obtained in the current time period. The multi-dimensional wear curve of the shield cutter in the current stratum includes wear curves of the shield cutter in multiple different dimensions in the current stratum. The second acquisition unit is used to acquire from the historical database multiple sets of multi-dimensional historical wear curves of the shield cutter in the current stratum that have the highest similarity to the multi-dimensional wear curve and the similarity is higher than a preset threshold. The optimization unit is used to optimize the model parameters of the shield cutter wear rate model in the current stratum based on the sampled data in the multiple sets of multi-dimensional historical wear curves, so as to obtain the optimized wear rate model of the shield cutter in the current stratum. The prediction unit is used to predict the wear of the tunnel boring machine cutter based on the optimized wear rate model of the cutter in the current stratum.

9. An electronic device, characterized in that, The device includes a memory, a processor, and a transceiver that are sequentially and communicatively connected. The memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the shield cutter wear prediction method as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or the instructions are executed by the computer, they implement the shield cutter wear prediction method as described in any one of claims 1 to 7.

Images