TBM cutterhead torque prediction method, system, equipment and medium

Abstract

The invention discloses a TBM cutterhead torque prediction method, system and device and a medium. The method comprises the steps that tunneling state parameter initial sample data influencing the cutterhead torque are obtained; the initial sample data are preprocessed, and abnormal tunneling state data in the TBM tunneling state parameters are removed; calculating the weight of each tunneling state parameter influence factor by adopting a rough set; selecting several characteristic parameters having the highest correlation with the cutterhead torque by using the rough set, forming a matrix by the characteristic parameters, and inputting the matrix into an LSTM neural network for training; and calculating a loss function according to TBM cutterhead torque prediction results output by the LSTM model in sequence, optimizing model parameters according to loss function calculation results, and finishing model training when training conditions are met to obtain a TBM cutterhead torque prediction model. According to the method and the system, the torque of the cutterhead can be quickly and accurately calculated in the tunneling process of the TBM equipment, so that reference is provided for an operator, the tunneling efficiency is improved, and equipment faults, cost increase and the like caused by improper selection of operation parameters are reduced.

Description

Technical Field

[0001] The present application relates to the field of deep learning technology, and in particular to a TBM cutterhead torque prediction method, system, device and medium. Background Art

[0002] TBM (Tunnel Boring Machine) is a large-scale special engineering machine used for rapid full-section excavation, and is widely used in tunnel construction projects such as hydropower, railways, and subways. The cutterhead is a key component of TBM excavation, directly bearing the total rock-breaking load from the hydraulic thrust cylinder, and is used to maintain the cutterhead's continuous rotation to break the rock in front. The cutterhead torque is one of the important performance parameters, which can provide the cutting force required for the cutterhead to break the rock, and has an important impact on the rock-breaking efficiency and rock-machine interaction.

[0003] There are many factors that affect the cutter head torque. The effects of each factor on the torque are different, and even vary greatly. Although a cutter head torque prediction model has been introduced in the prediction process of TBM cutter head torque, the existing cutter head torque prediction model still has large prediction errors due to the accuracy of the input parameters. Summary of the invention

[0004] The present application provides a TBM cutter head torque prediction method, system, device and medium to solve the above-mentioned problems.

[0005] In one aspect, the present application provides a method for predicting the torque of a TBM cutterhead, the method comprising the following steps:

[0006] Step S1: Obtaining TBM cutter head excavation state parameters;

[0007] Step S2: inputting the excavation state parameters into a pre-trained TBM cutter head torque prediction model for prediction; wherein the TBM cutter head torque prediction model is constructed based on an LSTM network model;

[0008] Step S3: Output the TBM cutter head torque prediction result.

[0009] In one implementation of the present application, step S2 specifically includes:

[0010] Step S21: obtaining initial sample data of excavation state parameters affecting cutter head torque;

[0011] Step S22: pre-processing the initial sample data to remove abnormal excavation state data in the excavation state parameters;

[0012] Step S23: using rough sets to select several characteristic parameters with the highest correlation with the cutter head torque, and inputting the matrix of the characteristic parameters into the LSTM neural network for training;

[0013] Step S24: Calculate the loss function according to the TBM cutter head torque prediction result output by the LSTM model, optimize the model parameters with the loss function calculation result, complete the model training when the training conditions are met, and obtain the TBM cutter head torque prediction model.

[0014] In one implementation of the present application, in step S21, the excavation state parameters affecting the cutter disc torque specifically include: propulsion speed v, total propulsion force F, penetration h, sum of motor torques Ts, cutter disc power W, sum of motor powers Ws, and cutter disc rotation speed n.

[0015] In an implementation of the present application, before step S23, the method further includes: calculating the weights of the influencing factors of each excavation state parameter.

[0016] In one implementation of the present application, in step S22, the abnormal excavation state data in the excavation state parameter is determined by the following formula:

[0017] F=f(v)×f(h)×f(n)

[0018]

[0019] In the formula, an F value of zero indicates that the shield machine is in a non-working state, and f(x) is a function for determining whether the cutter head speed n, tunneling speed v, and penetration h contain zero values. If the F value is zero, the recorded data is considered abnormal data.

[0020] In one implementation of the present application, the objective weight allocation process is as follows:

[0021] The importance calculation formula of the i-th attribute is:

[0022]

[0023] Where: C is the conditional attribute, D is the decision attribute; POS C (D) is the C positive domain of D; POS C-i (D) is the positive domain of the i-th conditional attribute of D;

[0024] The objective weight is calculated as follows:

[0025]

[0026] Where: r C-i (D) is the importance of the i-th attribute.

[0027] The present application also provides a TBM cutter head torque prediction system, the system comprising:

[0028] Data acquisition module, used to obtain TBM cutter head excavation status parameters;

[0029] A prediction module, used for inputting the excavation state parameters into a pre-trained TBM cutter head torque prediction model for prediction; wherein the TBM cutter head torque prediction model is constructed based on an LSTM network model;

[0030] The result output module is used to output the TBM cutter head torque prediction results.

[0031] In one implementation of the present application, the prediction module includes:

[0032] The preprocessing module is used to eliminate abnormal excavation status data in the TBM excavation status parameters.

[0033] The feature extraction module is used to select several feature parameters that are most correlated with the cutter head torque.

[0034] The training module is used to use the screened feature parameters as training samples, input them into the LSTM neural network for training, and optimize the model parameters with the loss function calculation results to complete the model training and obtain the TBM cutter head torque prediction model.

[0035] The torque calculation module is used to calculate the TBM cutter head torque according to the cutter head torque prediction model.

[0036] The present application also provides a TBM cutter head torque prediction device, the device comprising:

[0037] at least one processor; and,

[0038] a memory communicatively connected to the at least one processor; wherein,

[0039] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can complete the aforementioned TBM cutter head torque prediction method.

[0040] The present application also provides a non-volatile computer storage medium for TBM cutter head torque prediction, which stores computer executable instructions. The computer executable instructions are executed by a processor to implement the aforementioned TBM cutter head torque prediction method.

[0041] The present application provides a TBM cutterhead torque prediction method, system, device and medium, which can quickly and accurately calculate the cutterhead torque during the excavation process of TBM equipment, thereby providing a reference for the operator, improving the excavation efficiency, and reducing equipment failures and cost increases caused by improper selection of operating parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0043] Figure 1 A flow chart of a TBM cutter head torque prediction method provided in an embodiment of the present application;

[0044] Figure 2 A diagram showing the composition of a TBM cutterhead torque prediction system provided in an embodiment of the present application;

[0045] Figure 3 A schematic diagram of a TBM cutterhead torque prediction device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0047] The embodiments of the present application provide a TBM cutter head torque prediction method, system, device and medium. The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0048] Figure 1 A flow chart of a TBM cutter head torque prediction method provided in an embodiment of the present application. Figure 1 As shown, the method mainly includes the following steps:

[0049] Step S1: Obtaining TBM cutter head excavation state parameters;

[0050] Step S2: inputting the excavation state parameters into a pre-trained TBM cutter head torque prediction model for prediction; wherein the TBM cutter head torque prediction model is constructed based on an LSTM network model;

[0051] Step S3: Output the TBM cutter head torque prediction result.

[0052] In the embodiment of the present application, the step S2 specifically includes:

[0053] Step S21: obtaining initial sample data of excavation state parameters affecting cutter head torque;

[0054] Step S22: pre-processing the initial sample data to remove abnormal excavation state data in the excavation state parameters;

[0055] Step S23: using rough sets to select several characteristic parameters with the highest correlation with the cutter head torque, and inputting the matrix of the characteristic parameters into the LSTM neural network for training;

[0056] Step S24: Calculate the loss function according to the TBM cutter head torque prediction result output by the LSTM model, optimize the model parameters with the loss function calculation result, complete the model training when the training conditions are met, and obtain the TBM cutter head torque prediction model.

[0057] In the embodiment of the present application, in the step S21, the excavation state parameters affecting the cutter disc torque specifically include: propulsion speed v, total propulsion force F, penetration h, sum of motor torques Ts, cutter disc power W, sum of motor powers Ws, and cutter disc rotation speed n.

[0058] In the embodiment of the present application, before the step S23, the method further includes: calculating the weights of the influencing factors of each excavation state parameter.

[0059] In the embodiment of the present application, in step S22, the abnormal excavation state data in the excavation state parameter is determined by the following formula:

[0060] F=f(v)×f(h)×f(n)

[0061]

[0062] In the formula, an F value of zero indicates that the shield machine is in a non-working state, and f(x) is a function for determining whether the cutter head speed n, tunneling speed v, and penetration h contain zero values. If the F value is zero, the recorded data is considered abnormal data.

[0063] In the embodiment of the present application, the objective weight allocation process is as follows:

[0064] The importance calculation formula of the i-th attribute is:

[0065]

[0066] Where: C is the conditional attribute, D is the decision attribute; POS C (D) is the C positive domain of D; POS C-i (D) is the positive domain of the i-th conditional attribute of D;

[0067] The objective weight is calculated as follows:

[0068]

[0069] Where: r C-i (D) is the importance of the i-th attribute.

[0070] Long short-term memory network (LSTM) is a time-dependent recursive neural network that has a memory effect within a certain time range. The reason why the LSTM network model can solve the gradient explosion and gradient disappearance problems of RNN is that a gate mechanism (input gate, output gate, forget gate) is added to the structure of RNN to correct parameters. The LSTM network model consists of memory units, which are saved, written and read out through gate control.

[0071] The gate operation added by LSTM can extract the correlation information of parameters at different times of a continuous time series and use it to predict the output parameters at future times. It has the ability to predict. The update process of each gate and cell state of LSTM is shown in the following formula:

[0072] i t =σ(W i h t-1 +U i x t +b i );

[0073] a t =σ(W a h t-1 +U a x t +b a );

[0074] o t =σ(W o h t-1 +U o x t +b o );

[0075] h t =o t σ(C);

[0076] f t =σ(W f h t-1 +U f x t +b f );

[0077] C t =C t-1 ·f t+i t ·a t .

[0078] The above is a TBM cutter head torque prediction method provided in the embodiment of the present application. Based on the same inventive concept, the embodiment of the present application also provides a TBM cutter head torque prediction system. Figure 2 A composition diagram of a TBM cutter head torque prediction system provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the system mainly includes: a data acquisition module 201, used to obtain the TBM cutter head excavation state parameters; a prediction module 202, used to input the excavation state parameters into a pre-trained TBM cutter head torque prediction model for prediction; wherein the TBM cutter head torque prediction model is constructed based on the LSTM network model; a result output module 203, used to output the TBM cutter head torque prediction result.

[0079] In an embodiment of the present application, the prediction module includes: a preprocessing module for eliminating abnormal excavation state data in the TBM excavation state parameters. A feature extraction module for selecting several feature parameters with the highest correlation with the cutter head torque. A training module for using the selected feature parameters as training samples, inputting them into the LSTM neural network for training, and optimizing the model parameters with the loss function calculation results to complete the model training, and obtain the TBM cutter head torque prediction model. A torque calculation module for calculating the TBM cutter head torque according to the cutter head torque prediction model.

[0080] In the embodiment of the present application, taking the second phase of a city's rail transit construction project as an example, the length of its shield tunnel section is 3965m, of which 56% of the sections pass through medium-weathered andesite, and the remaining sections mainly pass through composite strata composed of clay, sand, strongly weathered andesite and medium-weathered andesite. The project adopts a composite earth pressure balance shield with a cutter head diameter of 7640mm, a maximum thrust of 47756KN, a maximum excavation rate of 120mm / min, and an escape torque of 8400N·m. The cutter head adopts the form of "4 spokes + 4 panels" with an opening rate of 40%. It is equipped with 8 center hobs, 24 front hobs, and 12 edge hobs. The hob has a highly wear-resistant alloy tooth cutting ring with a cutter ring diameter of 18in.

[0081] According to engineering practice, there is a nonlinear mathematical relationship between the excavation rate, cutterhead torque and other excavation data during the excavation process. Each geological segmented shield records the excavation parameters of each ring, and a total of 160 rings of data are collected. They are input into the LSTM network model as linear regression samples for training, with the training set accounting for 80% and the test set accounting for 20%. After optimization, they can meet the torque prediction.

[0082] In the embodiment of the present application, the LSTM network model is used to predict the cutter disc torque as shown in Table 1 below.

[0083] Table 1 Shield machine cutter head torque prediction table

[0084]

[0085] The above is a TBM cutter head torque prediction system provided by the embodiment of the present application. Based on the same inventive concept, the embodiment of the present application also provides a TBM cutter head torque prediction device. Figure 3 A schematic diagram of a TBM cutter head torque prediction device provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the device mainly includes: at least one processor 301; and a memory 302 that is communicatively connected to the at least one processor; wherein the memory 302 stores instructions that can be executed by the at least one processor 301, and the instructions are executed by the at least one processor 301 so that the at least one processor 301 can complete the aforementioned TBM cutter head torque prediction method.

[0086] In addition, an embodiment of the present application further provides a non-volatile computer storage medium for TBM cutter head torque prediction, which stores computer executable instructions, and the computer executable instructions are executed by a processor to implement the aforementioned TBM cutter head torque prediction method.

[0087] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0088] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0089] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0090] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0091] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0092] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0093] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A TBM cutter head torque prediction method, characterized in that: The method comprises the following steps: Step S1: Obtaining TBM cutter head excavation state parameters; Step S2: inputting the excavation state parameters into a pre-trained TBM cutter head torque prediction model for prediction; wherein the TBM cutter head torque prediction model is constructed based on an LSTM network model; Step S3: Output the TBM cutter head torque prediction result.

2. A TBM cutter head torque prediction method according to claim 1, characterized in that: The step S2 specifically includes: Step S21: obtaining initial sample data of excavation state parameters affecting cutter head torque; Step S22: pre-processing the initial sample data to remove abnormal excavation state data in the excavation state parameters; Step S23: using rough sets to select several characteristic parameters with the highest correlation with the cutter head torque, and inputting the matrix of the characteristic parameters into the LSTM neural network for training; Step S24: Calculate the loss function according to the TBM cutter head torque prediction result output by the LSTM model, optimize the model parameters with the loss function calculation result, complete the model training when the training conditions are met, and obtain the TBM cutter head torque prediction model.

3. A TBM cutter head torque prediction method according to claim 2, characterized in that: In the step S21, the excavation state parameters affecting the cutter head torque specifically include: propulsion speed v, total propulsion force F, penetration h, sum of motor torques Ts, cutter head power W, sum of motor powers Ws, and cutter head rotation speed n.

4. A TBM cutter head torque prediction method according to claim 2, characterized in that: Before step S23, the method further includes: calculating the weights of the influencing factors of each excavation state parameter.

5. A TBM cutter head torque prediction method according to claim 2, characterized in that: In step S22, the abnormal excavation state data in the excavation state parameter is determined by the following formula: F=f(v)×f(h)×f(n) In the formula, an F value of zero indicates that the shield machine is in a non-working state, and f(x) is a function for determining whether the cutter head speed n, tunneling speed v, and penetration h contain zero values. If the F value is zero, the recorded data is considered abnormal data.

6. A TBM cutter head torque prediction method according to claim 4, characterized in that: The process of objective weight allocation is as follows: The importance calculation formula of the i-th attribute is: Where: C is the conditional attribute, D is the decision attribute; POS C (D) is the C positive domain of D; POS C-i (D) is the positive domain of the i-th conditional attribute of D; The objective weight is calculated as follows: Where: r C-i (D) is the importance of the i-th attribute.

7. A TBM cutterhead torque prediction system, characterized in that: The system comprises: Data acquisition module, used to obtain TBM cutter head excavation status parameters; A prediction module, used for inputting the excavation state parameters into a pre-trained TBM cutter head torque prediction model for prediction; wherein the TBM cutter head torque prediction model is constructed based on an LSTM network model; The result output module is used to output the TBM cutter head torque prediction results.

8. The TBM cutter head torque prediction system according to claim 7, characterized in that: The prediction module comprises: A pre-processing module is used to remove abnormal excavation state data from TBM excavation state parameters; A feature extraction module is used to select several feature parameters that are most correlated with the cutter head torque; The training module is used to use the screened feature parameters as training samples, input them into the LSTM neural network for training, and optimize the model parameters with the loss function calculation results to complete the model training and obtain the TBM cutter head torque prediction model. The torque calculation module is used to calculate the TBM cutter head torque according to the cutter head torque prediction model.

9. A TBM cutter head torque prediction device, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can complete the TBM cutter head torque prediction method described in any one of claims 1-7.

10. A non-volatile computer storage medium for predicting TBM cutterhead torque, storing computer executable instructions, characterized in that: The computer executable instructions are executed by a processor to implement a TBM cutter head torque prediction method as described in any one of claims 1-7.

Images