Tunneling machine TBM navigation orientation method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of intelligent coal mines, in particular to a heading machine TBM navigation orientation method and device, electronic equipment and a storage medium. The method comprises the steps that a plurality of tunneling relevant parameters of the TBM are obtained, the tunneling relevant parameters comprise the propelling speed, the penetration degree, the cutterhead thrust, the cutterhead rotating speed and the cutterhead torque, the tunneling relevant parameter data are preprocessed and subjected to feature extraction, and the movement trend of the TBM of the tunneling machine in the future preset time period is determined according to the extracted features; therefore, navigation orientation control is carried out, so that the TBM executes a tunneling task according to a preset tunneling route. The problem that due to the fact that the attitude adjustment time of the heading machine is late, the deviation of the heading route is large is solved, the attitude adjustment of the heading machine is automatic and intelligent, and support is provided for improving the working efficiency of coal mining.

Description

Technical Field

[0001] The present application relates to the field of intelligent coal mine technology, and more specifically, to a TBM navigation and orientation method, device, electronic device and storage medium. Background Art

[0002] With the increasing demand for coal mining, the application of tunnel boring machines (TBMs), one of the most important equipment for domestic tunnel construction, in the field of coal mining has developed rapidly. Tunnel boring machines mine according to the predetermined design route, but during the excavation process, the posture of the TBM may deviate from the design route.

[0003] There are mainly two solutions in the relevant technology: First, rely on the experience of the tunnel boring machine operator to adjust the posture during the excavation process. This method has the problem of difficult adjustment and high cost; second, detect the posture of the tunnel boring machine in real time and make real-time adjustments. This method cannot predict its future excavation route, resulting in low accuracy and poor effect of the tunnel boring machine posture adjustment. Summary of the invention

[0004] In view of this, one of the technical problems solved by the embodiments of the present application is to provide a TBM navigation and orientation method, device, electronic device and storage medium, which utilizes the time domain and frequency domain feature analysis of multiple tunneling-related parameters to predict the movement trend of the tunneling machine, thereby avoiding the problem of large tunneling route deviation caused by late adjustment of the tunneling machine's posture, thereby improving the accuracy and reliability of TBM navigation and orientation, and providing technical support for the efficient construction of rock tunnels.

[0005] In a first aspect of the embodiments of the present application, a TBM navigation and orientation method is disclosed, the method comprising:

[0006] Obtain multiple tunneling-related parameters of the TBM, including propulsion speed, penetration, cutterhead thrust, cutterhead speed, and cutterhead torque;

[0007] Preprocessing a plurality of tunneling related parameter data to obtain a plurality of preprocessed tunneling related parameters;

[0008] Extract the features of multiple pre-processed tunneling related parameters in the time domain and frequency domain, and determine the movement trend of the tunnel boring machine TBM in the future predetermined time period based on the extracted features;

[0009] The TBM is navigated and directional-controlled according to the movement trend, so that the TBM can perform the excavation task according to the predetermined excavation route.

[0010] In a second aspect of the embodiment of the present application, a navigation and orientation device for a tunnel boring machine (TBM) is disclosed, the device comprising:

[0011] A data acquisition module is used to acquire multiple tunneling related parameters of the TBM, including propulsion speed, penetration, cutter head thrust, cutter head speed and cutter head torque;

[0012] A data preprocessing module is used to preprocess a plurality of tunneling related parameter data to obtain a plurality of preprocessed tunneling related parameters;

[0013] The trend prediction module is used to extract the features of multiple pre-processed tunneling related parameters in the time domain and frequency domain, and determine the movement trend of the tunneling machine TBM within a predetermined time period in the future based on the extracted features;

[0014] The navigation and orientation module is used to perform navigation and orientation control on the TBM according to the movement trend, so that the TBM can perform the excavation task according to the predetermined excavation route.

[0015] In a third aspect of an embodiment of the present application, an electronic device is disclosed. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above method are implemented.

[0016] In a fourth aspect of the embodiments of the present application, a computer-readable storage medium is disclosed, which stores a computer program. When the computer program is executed by a processor, the steps of the above method are implemented.

[0017] The present application has the following advantages: by obtaining the tunneling related parameters of the TBM including the propulsion speed, penetration, cutterhead thrust, cutterhead rotation speed and cutterhead torque, and performing feature extraction in the time domain and frequency domain after preprocessing, it plays a role in avoiding the influence of noise and other factors on the subsequently extracted features, thereby making the movement trend of the TBM determined based on the extracted features, further providing a judgment basis for determining whether the TBM deviates from the predetermined tunneling route, and navigating and orienting the TBM based on the judgment result, not only achieving the purpose of arranging the influencing factors related to tunneling in time series to predict the movement trend, but also achieving the effect of advancing the timing of correcting the posture of the tunneling machine, avoiding the problem of large deviation of the tunneling route caused by the late adjustment of the posture of the tunneling machine, achieving the automation and intelligence of the posture adjustment of the tunneling machine, and providing support for improving the operating efficiency of coal mining. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of a process flow of a TBM navigation and orientation method provided in one embodiment of the present application;

[0019] Figure 2 A schematic diagram showing the comparison before and after preprocessing in a TBM navigation and orientation method provided by an embodiment of the present application;

[0020] Figure 3 A schematic structural diagram of a TBM navigation and orientation device provided in accordance with an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0022] It should be noted that although the functional modules are divided in the device schematic and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart.

[0023] First, several terms involved in this application are introduced and explained:

[0024] In the embodiment of the present application, the tunnel boring machine TBM mainly includes a hard rock tunnel boring machine (TBM) used in hard rock strata with good excavation face stability and surrounding rock supportability and high excavation strata hardness, and a shield machine used in soft soil strata.

[0025] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0026] According to one embodiment of the present application, a TBM navigation and orientation method is provided, such as Figure 1 As shown, the method includes steps S101 to S104.

[0027] Step S101: Acquire multiple tunneling related parameters of the TBM, where the tunneling related parameters include propulsion speed, penetration, cutter head thrust, cutter head rotation speed and cutter head torque.

[0028] Specifically, the storage records of the TBM can be acquired in real time, and excavation-related parameters including propulsion speed, penetration rate, cutterhead thrust, cutterhead rotation speed, and cutterhead torque can be selected therefrom. It is also possible to directly generate acquisition instructions for excavation-related parameters, eliminating the need to screen from the storage records of the TBM, thereby quickly determining excavation-related parameters and reducing the calculation overhead of the navigation and orientation center.

[0029] Step S102: Preprocessing a plurality of tunneling-related parameter data to obtain a plurality of preprocessed tunneling-related parameters.

[0030] Specifically, preprocessing generally includes data denoising, data calibration, data synchronization and other operations. In specific implementation, data denoising can use a preset filtering algorithm (such as Kalman filtering algorithm) to remove noise in propulsion-related parameters to avoid the impact of noise on subsequent data processing; data synchronization is mainly to ensure the synchronization of tunneling-related parameters in time.

[0031] Step S103: extracting features in the time domain and frequency domain for a plurality of pre-processed tunneling related parameters, and determining the movement trend of the tunnel boring machine TBM within a predetermined time period in the future based on the extracted features.

[0032] The embodiment of the present application simultaneously extracts the time domain characteristics and frequency domain characteristics of the tunneling related parameters, thereby comprehensively considering the factors affecting the posture of the tunnel boring machine TBM and improving the prediction accuracy of the movement trend of the tunnel boring machine TBM.

[0033] Specifically, you can choose from a preset algorithm library based on the specific features to be extracted. The algorithm library provides multiple algorithms corresponding to different features, and you can choose one of them as the extraction model for the corresponding feature based on the selected operation. For example, if you want to extract the mean, you can determine the algorithm for extracting the mean based on the pre-selected operations among multiple algorithms for the mean.

[0034] Specifically, a feature extraction model for extracting multiple features can be constructed. For example, a convolutional neural network (CNN) can be used for feature extraction, thereby achieving the purpose of extracting multiple features using one model and realizing the purpose of intelligent feature extraction.

[0035] In the embodiment of the present application, the motion trend is used to characterize the position change trajectory of the posture parameters of the roadheader TBM at different time points.

[0036] Step S104: Navigation and orientation control are performed on the TBM according to the movement trend, so that the TBM performs the tunneling task according to the predetermined tunneling route.

[0037] Specifically, the movement trend can be visualized as at least one of a specific numerical value and a chart. In specific implementation, the movement trend and the predetermined excavation route can be superimposed and displayed in the form of a linear trend chart, so as to achieve the purpose of characterizing whether the excavation is deviated by the overlap of the two linear trends output visually.

[0038] The embodiment of the present application obtains tunneling related parameters of the TBM including propulsion speed, penetration, cutterhead thrust, cutterhead rotation speed, and cutterhead torque, and extracts features in the time domain and frequency domain after preprocessing, thereby avoiding the influence of factors such as noise on the subsequently extracted features, so that the movement trend of the TBM determined based on the extracted features further provides a judgment basis for determining whether the TBM deviates from the predetermined tunneling route, and navigates and orients the TBM based on the judgment result, which not only achieves the purpose of arranging the influencing factors related to tunneling in time series to predict the movement trend, but also has the effect of advancing the timing of correcting the posture of the tunneling machine, avoiding the problem of large tunneling route deviation caused by late adjustment of the posture of the tunneling machine, achieving automation and intelligence of the posture adjustment of the tunneling machine, and providing support for improving the operating efficiency of coal mining.

[0039] In some embodiments, preprocessing includes at least operations such as data cleaning and outlier removal.

[0040] Specifically, tunneling-related parameters may cause abnormal data (such as too large, too small, or empty values) in a certain period of time or time point due to equipment failure, operation progress, etc., thereby affecting the accuracy of subsequent extracted features.

[0041] Specifically, a data cleaning algorithm may be pre-set to adjust the range of abnormal data to be filtered according to the working conditions or cleaning intensity.

[0042] In some embodiments, step S102 further includes:

[0043] Step S1021 (not shown in the figure): determining the excavation status at different time points among a plurality of excavation-related parameters;

[0044] Step S1022 (not shown in the figure): if the excavation state at any time point in any excavation-related parameter is non-excavation, the data whose excavation state is non-excavation is eliminated.

[0045] In the embodiment of the present application, the excavation status is used to characterize the working status of the tunnel boring machine TBM. For example, the tunnel boring machine TBM is in the process of performing the excavation task. During the TBM excavation process, a large amount of data in the non-excavation state will be generated due to processes such as shoe step changing, surrounding rock support, tool replacement, and shutdown inspection and maintenance, which will interfere with the analysis of the normal cycle excavation status data.

[0046] In some embodiments, before step S1021, it also includes: constructing a binary state discrimination function based on the cutter disc thrust, cutter disc torque, cutter disc rotation speed and propulsion speed; step S1021 further includes: calculating the data of each time point of the excavation related parameters respectively, and when the value of the binary state discrimination function of the data at any time point is 0, determining that the excavation state of any excavation related parameter at the corresponding time point is a non-excavation state.

[0047] Specifically, a binary state discriminant function can be constructed using at least one indicator of the excavation-related parameters to determine whether the TBM is in a working state. In this embodiment, the cutterhead thrust F, cutterhead torque T, cutterhead rotation speed N and propulsion speed V are used as evaluation indicators to determine whether the TBM is in a non-excavation state, and a binary state discriminant function is constructed. When the constructed discriminant function is 0, it is determined that the TBM is in a non-excavation state and the data needs to be eliminated; when the discriminant function is 1, it is determined that the TBM is in a working state and the data is retained. The constructed discriminant function is as follows:

[0048] I=f(F)f(T)f(N)f(V)f(V);

[0049]

[0050] Wherein, I represents the discriminant function, and x represents the cutter head thrust F, cutter head torque T, cutter head rotation speed N and propulsion speed V. Specifically, during the processing, each indicator at each moment is calculated one by one, and then the idle period data with I=0 is eliminated.

[0051] In some other embodiments, step S102 further includes:

[0052] Comparing the values ​​of the plurality of excavation-related parameters at any time point with the lower edge values ​​and the upper edge values ​​of the excavation-related parameters;

[0053] If the value of any excavation-related parameter at any time point is less than the lower edge value, or greater than the upper edge value, then the value of the excavation-related parameter at any time point is determined to be an abnormal value;

[0054] The value of any excavation-related parameter at any time point is eliminated, and the value of any time point is subjected to difference processing using a preset interpolation algorithm.

[0055] During the TBM excavation process, due to the complexity of the geological conditions of the excavation strata and the subjectivity of the operation of the TBM driver, some abnormal values ​​exist in the original data and need to be eliminated. In order to solve the problem of abnormal values ​​and missing values, this embodiment uses the quartile method to identify abnormal data and uses the Lagrange interpolation method to interpolate the deleted or missing data. Specifically, the quartile method abnormal value judgment formula is:

[0056] L lower =Q1-1.5IQR;

[0057] L upper =Q3+1.5IQR;

[0058] IQR=Q3-Q1;

[0059]

[0060] Among them, Q3 represents the upper quarterback number, Q1 represents the lower quarterback number, IQR represents the interquartile range, L lower Represents the lower limit of non-outlier values, L upper Represents the upper limit of non-outliers.

[0061] Combine the following Figure 2 As an example, data cleaning is explained. In the figure, some TBM excavation parameters are used as data preprocessing objects, and the selected 3 cycle data show several common working conditions in the TBM excavation process. As shown in Figure (a), the first cycle shows the complete cycle process of TBM excavation, including the shutdown section, the start-up section, the stable excavation section and the stop-down section; in the second cycle, the excavation data abnormal values ​​can be clearly seen; in the third cycle, at 150-155 minutes, all parameters instantly dropped to zero and returned to normal in a short time. This stage is the equipment failure maintenance section. Through the data preprocessing process, non-excavation sections and abnormal values ​​are eliminated to obtain the TBM excavation parameter data preprocessing results, as shown in Figure (b).

[0062] In some embodiments, step S103 further includes:

[0063] Step S1031 (not shown in the figure): input multiple pre-processed tunneling related parameters into the trained motion trend prediction model to obtain various posture parameters of the tunnel boring machine TBM in a predetermined time period in the future. The motion trend prediction model includes an input layer, a first convolution layer, a second convolution layer, a pooling layer, a first long short-term memory LSTM layer, a second long short-term memory LSTM layer, a third long short-term memory LSTM layer, a fully connected layer and an output layer connected in sequence;

[0064] Step S1032 (not shown): Graphing is performed based on various posture parameters of the tunnel boring machine TBM within a predetermined time period in the future to obtain a movement trend, wherein the posture parameters include roll angle, pitch angle, azimuth angle and horizontal deviation.

[0065] The embodiment of the present application combines the convolutional neural network CNN and the long short-term memory LSTM network through the setting of two convolutional layers, three LSTM layers, a fully connected layer and an output layer, and simultaneously extracts the time domain features and frequency domain features of the data, and temporally correlates the factors affecting the posture of the tunnel boring machine TBM, thereby achieving the purpose of predicting the motion trend of the tunnel boring machine TBM, and at the same time can improve the diversity and accuracy of feature extraction of the neural network model, as well as the prediction accuracy of motion trends.

[0066] During specific implementation, each layer structure of the motion trend prediction model can be set with reference to Table 1.

[0067] Table 1

[0068]

[0069] In some embodiments, before step S1031, the method further includes:

[0070] Obtaining sample data for a roadheader TBM marked with tunneling related parameters and their corresponding posture parameters, the sample data including a training sample set and a test sample set;

[0071] The initialization prediction model constructed by the sparrow optimization algorithm is trained using the training sample set, and verified using the test sample set, until the prediction error values ​​of each item predicted by the trained motion trend prediction model are less than the predetermined error threshold, thereby obtaining a trained motion trend prediction model.

[0072] Specifically, the sample data may be divided into a training sample set and a test sample set according to a preset ratio, for example, a ratio of 7:3.

[0073] Specifically, when evaluating the trained model using the test sample set, six evaluation indicators, namely mean absolute error (MAE), mean absolute percentage error (MAPE), mean square error (MSE), root mean square error (RMSE), correlation coefficient (R), and determination coefficient (R2), can be used to comprehensively evaluate the prediction results of the model. Among them, the mean absolute error can intuitively reflect the error size of the model, while the mean absolute percentage error more clearly shows the relative size of the error; the mean square error provides the square magnitude of the error, while the root mean square error combines the square error and gives a more interpretable result; the correlation coefficient measures the degree of linear relationship between the model and the actual observation, while the determination coefficient quantifies the model's ability to explain data variation. Taking these indicators into consideration can comprehensively evaluate the prediction performance of the model, so as to better understand the performance of the model in practical applications.

[0074] In some embodiments, before step S1031 of obtaining sample data for a roadheader TBM marked with tunneling related parameters and their corresponding posture parameters, the method includes:

[0075] Get historical data for TBMs;

[0076] Pearson correlation analysis is performed on several characteristic parameters of historical data, and multiple tunneling related parameters are screened out from the several characteristic parameters based on the analysis results.

[0077] Specifically, more than 200 characteristic parameters are recorded in the historical data, many of which have no relevance to the predicted TBM posture. Therefore, it is necessary to screen these parameters to select the excavation-related parameters that are relevant to the predicted TBM posture.

[0078] In the embodiments of the present application, Pearson correlation analysis is a statistical method used to measure the strength and direction of the linear relationship between two continuous variables. Its results are usually expressed as the Pearson correlation coefficient, which ranges from -1 to 1. (1) When the correlation coefficient is 1, it indicates a perfect positive correlation, that is, the two variables are linearly positively correlated. When one variable increases, the other variable also increases. (2) When the correlation coefficient is -1, it indicates a perfect negative correlation, that is, the two variables are linearly negatively correlated. When one variable increases, the other variable decreases. (3) When the correlation coefficient is 0, it indicates that there is no linear relationship, but it does not mean that there is no other type of relationship between the two variables.

[0079] The specific calculation formula of Pearson correlation coefficient is:

[0080]

[0081] Among them, X i and Y i are the observed values ​​of the two variables, X and Y are the means of the two variables, and ∑ represents the summation operation.

[0082] After calculation, there are 5 parameters for model training and 4 output feature parameters, as shown in Table 2.

[0083] Table 2

[0084]

[0085] Through the above analysis, the tunneling related parameters (i.e., propulsion speed, penetration, cutterhead thrust, cutterhead speed, and cutterhead torque) in the historical data of the TBM are marked, and the corresponding posture parameters (i.e., roll angle, pitch angle, azimuth angle, and horizontal deviation) are marked to obtain sample data for model training.

[0086] In some other embodiments, step S103 further includes:

[0087] Input the pre-processing excavation related parameters into the trained CNN neural network model and the trained BiLSTM bidirectional long short-term memory network model respectively to obtain the first output result and the second output result;

[0088] The first output result and the second output result are spliced ​​and input into a pre-built trajectory prediction model to obtain a predicted motion trend.

[0089] This application uses two independent models for feature extraction, which enables flexible model selection and separate training. It can control the model performance effect at any time according to the prediction accuracy requirements, so as to achieve the purpose of improving the model training accuracy according to the scenario requirements.

[0090] In some embodiments, step S104 further includes:

[0091] Match the movement trend with the excavation route to obtain information related to the excavation deviation of the TBM;

[0092] A posture calibration instruction is generated according to the information related to the excavation deviation, and the posture calibration instruction is sent to the tunnel boring machine TBM, so that the tunnel boring machine TBM performs the excavation task along the excavation route according to the posture calibration instruction.

[0093] In the embodiment of the present application, the information related to the excavation deviation is used to characterize the horizontal deviation, pitch angle deviation, and rolling deviation of the tunnel boring machine TBM from the designed axis during the excavation process.

[0094] Specifically, the posture calibration instruction can be sent to the tunnel boring machine TBM, so that it can adjust its posture according to the control instruction, thereby correcting the posture deviation by adjusting the support shoes and the support hydraulic cylinder.

[0095] Specifically, corresponding early warning prompts can be generated based on the information related to the excavation deviation and visually output (in the form of text, charts, etc.) so that users can read visually through the terminal, thereby improving user readability.

[0096] An embodiment of the present application provides a navigation and orientation device for a tunnel boring machine (TBM), such as Figure 3 As shown, the device 30 includes: a data acquisition module 301, a data preprocessing module 302, a trend prediction module 303, and a navigation orientation module 304.

[0097] The data acquisition module 301 is used to acquire a plurality of tunneling related parameters of the tunnel boring machine TBM, wherein the tunneling related parameters include propulsion speed, penetration, cutter head thrust, cutter head rotation speed and cutter head torque;

[0098] The data preprocessing module 302 is used to preprocess a plurality of tunneling related parameter data to obtain a plurality of preprocessed tunneling related parameters;

[0099] The trend prediction module 303 is used to extract the characteristics of the multiple pre-processed tunneling related parameters in the time domain and the frequency domain, and determine the movement trend of the tunneling machine TBM in a predetermined time period in the future according to the extracted characteristics;

[0100] The navigation and orientation module 304 is used to perform navigation and orientation control on the TBM according to the movement trend, so that the TBM performs the excavation task according to the predetermined excavation route.

[0101] The embodiment of the present application obtains tunneling related parameters of the TBM including propulsion speed, penetration, cutterhead thrust, cutterhead rotation speed, and cutterhead torque, and extracts features in the time domain and frequency domain after preprocessing, thereby avoiding the influence of factors such as noise on the subsequently extracted features, so that the movement trend of the TBM determined based on the extracted features further provides a judgment basis for determining whether the TBM deviates from the predetermined tunneling route, and navigates and orients the TBM based on the judgment result, which not only achieves the purpose of arranging the influencing factors related to tunneling in time series to predict the movement trend, but also has the effect of advancing the timing of correcting the posture of the tunneling machine, avoiding the problem of large tunneling route deviation caused by late adjustment of the posture of the tunneling machine, achieving automation and intelligence of the posture adjustment of the tunneling machine, and providing support for improving the operating efficiency of coal mining.

[0102] In some embodiments, preprocessing includes at least data cleaning, outlier removal, etc.

[0103] Furthermore, the data preprocessing module includes

[0104] A state determination submodule is used to determine the excavation state at different time points among multiple excavation related parameters;

[0105] The first elimination submodule is used to eliminate the data of any excavation related parameter at any time point if the excavation state of the excavation related parameter at any time point is non-excavation.

[0106] Furthermore, the state determination submodule also includes a function construction unit and a state determination unit, wherein the function construction unit is used to construct a binary state discrimination function based on the cutter disc thrust, cutter disc torque, cutter disc rotation speed and propulsion speed; the state determination unit is used to calculate the data of each time point of multiple excavation related parameters respectively, and when the value of the binary state discrimination function of any excavation related parameter at any time point is 0, the excavation state of any excavation related parameter at the corresponding time point is determined to be a non-excavation state.

[0107] Furthermore, the data preprocessing module includes:

[0108] A parameter comparison submodule, used to compare the values ​​of multiple excavation related parameters at any time point with a preset minimum value and a preset maximum value;

[0109] An abnormal value determination submodule is used to determine that the value of any excavation-related parameter at any time point is an abnormal value if the value of the excavation-related parameter at any time point is less than a preset minimum value, or greater than a preset maximum value;

[0110] The second elimination submodule is used to eliminate the value of any excavation related parameter at any time point, and use a preset interpolation algorithm to perform difference processing on the data at any time point.

[0111] Furthermore, the trend prediction module includes:

[0112] The first model processing submodule is used to input the pre-processed tunneling related parameters into the trained motion trend prediction model to obtain various posture parameters of the tunnel boring machine TBM within a predetermined time period in the future. The motion trend prediction model includes an input layer, a first convolution layer, a second convolution layer, a pooling layer, a first short-term memory LSTM layer, a second short-term memory LSTM layer, a third short-term memory LSTM layer, a fully connected layer and an output layer connected in sequence. The posture parameters include rolling angle, pitch angle, azimuth angle and horizontal deviation;

[0113] The first trend determination submodule is used to draw a graph based on various posture parameters of the tunnel boring machine TBM within a predetermined time period in the future to obtain a movement trend.

[0114] Furthermore, before the trend prediction module inputs the pre-processed tunneling related parameters into the trained motion trend prediction model to obtain various posture parameters of the tunnel boring machine TBM within a predetermined time period in the future, it also includes:

[0115] The sample acquisition submodule is used to acquire sample data marked with tunneling related parameters and their corresponding posture parameters for the tunnel boring machine TBM, and the sample data includes a training sample set and a test sample set;

[0116] The model training submodule is used to train the initialization prediction model constructed by the sparrow optimization algorithm using the training sample set, and verify it using the test sample set until the prediction error values ​​of each item predicted by the trained motion trend prediction model are less than the predetermined error threshold, thereby obtaining a trained motion trend prediction model.

[0117] Furthermore, before the sample acquisition submodule acquires sample data marked with tunneling related parameters and their corresponding posture parameters for the tunnel boring machine TBM, the method includes:

[0118] A historical data acquisition unit, used for acquiring historical data for a roadheader TBM;

[0119] The historical data screening unit is used to perform Pearson correlation analysis on several characteristic parameters of the historical data, and screen out multiple excavation related parameters from the several characteristic parameters based on the analysis results.

[0120] Furthermore, the trend prediction module includes:

[0121] The second prediction processing submodule is used to input the pre-processing tunneling related parameters into the trained CNN neural network model and the trained BiLSTM bidirectional long short-term memory network model respectively to obtain the first output result and the second output result;

[0122] The second trend determination submodule is used to splice the first output result and the second output result and input them into a pre-built trajectory prediction model to obtain a predicted motion trend.

[0123] Furthermore, the navigation and orientation module includes:

[0124] The deviation information determination submodule is used to match the movement trend with the excavation route to obtain the excavation deviation related information of the TBM;

[0125] The deviation information processing submodule is used to generate a posture calibration instruction based on the excavation deviation related information, and send the posture calibration instruction to the tunnel boring machine TBM, so that the tunnel boring machine TBM performs the excavation task along the excavation route according to the posture calibration instruction.

[0126] Yet another embodiment of the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-readable instructions, and the processor is configured to execute the computer-readable instructions, wherein the computer-readable instructions execute the above method when executed.

[0127] Specifically, the processor may be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0128] Specifically, the processor is connected to the memory via a bus, and the bus may include a path for transmitting information. The bus may be a PCI bus or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc.

[0129] The memory can be a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, or an EEPROM, CD-ROM or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this.

[0130] Optionally, the memory is used to store the code of the computer program for executing the solution of the present application, and the execution is controlled by the processor. The processor is used to execute the application program code stored in the memory to implement Figure 3 The illustrated embodiments provide for the operation of the apparatus.

[0131] Another embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions for executing the above-mentioned Figure 1 The method shown.

[0132] The device embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] It will be appreciated by those skilled in the art that all or some of the steps and systems in the disclosed method above may be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that may be used to store desired information and may be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0134] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the above-mentioned implementation mode. Technical personnel familiar with the field can also make various equivalent deformations or substitutions without violating the spirit of the present application. These equivalent deformations or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A TBM navigation and orientation method, characterized in that: The method comprises: Acquire multiple tunneling related parameters of the tunnel boring machine (TBM), wherein the tunneling related parameters include advancement speed, penetration, cutter head thrust, cutter head rotation speed, and cutter head torque; Preprocessing the plurality of tunneling-related parameter data to obtain a plurality of preprocessed tunneling-related parameters; Extracting features in the time domain and frequency domain for the plurality of pre-processed tunneling related parameters, and determining the movement trend of the tunnel boring machine TBM within a predetermined time period in the future according to the extracted features; The TBM is navigated and directional-controlled according to the movement trend, so that the TBM performs the excavation task according to a predetermined excavation route.

2. The method according to claim 1, characterized in that: The preprocessing of the plurality of tunneling related parameter data to obtain a plurality of preprocessed tunneling related parameters includes: Determine the excavation status at different time points among the plurality of excavation-related parameters; If the excavation state at any time point in any of the excavation-related parameters is non-excavation, the data with the excavation state being non-excavation will be eliminated.

3. The method according to claim 2, characterized in that Before determining the excavation status of the plurality of excavation related parameters at different time points, the method includes: According to the cutter head thrust, cutter head torque, cutter head rotation speed and propulsion speed, a binary state discrimination function is constructed; The determining of the excavation status at different time points among the plurality of excavation related parameters comprises: The data of the multiple excavation related parameters at each time point are calculated respectively, and when the value of the binary state discriminant function of the data of any excavation related parameter at any time point is 0, the excavation state of any of the excavation related parameters at the corresponding time point is determined to be a non-excavation state.

4. The method according to claim 1, characterized in that The preprocessing of the plurality of tunneling related parameter data to obtain a plurality of preprocessed tunneling related parameters includes: Compare the values ​​of the plurality of excavation-related parameters at any time point with a preset minimum value and a preset maximum value; If the value of any of the excavation related parameters at any time point is less than a preset minimum value, or greater than a preset maximum value, then the value of any of the excavation related parameters at any time point is determined to be an abnormal value; The value of any of the excavation-related parameters at any time point is eliminated, and the data at any time point is subjected to difference processing using a preset interpolation algorithm.

5. The method according to claim 1, characterized in that: The step of extracting features in the time domain and the frequency domain from the plurality of pre-processed tunneling related parameters, and determining the movement trend of the tunnel boring machine TBM within a predetermined time period in the future according to the extracted features, comprises: Input the pre-processed excavation related parameters into the trained motion trend prediction model to obtain various posture parameters of the tunnel boring machine TBM in a predetermined time period in the future, wherein the motion trend prediction model includes an input layer, a first convolution layer, a second convolution layer, a pooling layer, a first long short-term memory LSTM layer, a second long short-term memory LSTM layer, a third long short-term memory LSTM layer, a fully connected layer and an output layer connected in sequence, and the posture parameters include a roll angle, a pitch angle, an azimuth angle and a horizontal deviation; The motion trend is obtained by drawing a graph based on the various posture parameters of the tunnel boring machine TBM within a predetermined time period in the future.

6. The method according to claim 5, characterized in that Before inputting the pre-processed excavation related parameters into the trained motion trend prediction model to obtain various posture parameters of the roadheader TBM within a predetermined time period in the future, the method further includes: Acquire sample data for the roadheader TBM marked with tunneling related parameters and the corresponding posture parameters, wherein the sample data includes a training sample set and a test sample set; The initialization prediction model constructed by using the sparrow optimization algorithm is trained using the training sample set, and verified using the test sample set, until the prediction error values ​​of each item predicted by the trained motion trend prediction model are less than a predetermined error threshold, thereby obtaining the trained motion trend prediction model.

7. The method according to claim 6, characterized in that Before obtaining sample data marked with excavation-related parameters and their corresponding posture parameters for the roadheader TBM, the method includes: Acquiring historical data for the roadheader TBM; A Pearson correlation analysis is performed on several characteristic parameters of the historical data, and a plurality of the tunneling related parameters are screened out from the several characteristic parameters based on the analysis result.

8. The method according to claim 1, characterized in that The step of extracting features in the time domain and the frequency domain from the plurality of pre-processed tunneling related parameters, and determining the movement trend of the tunnel boring machine TBM within a predetermined time period in the future according to the extracted features, comprises: Inputting the pre-processing excavation related parameters into the trained CNN neural network model and the trained BiLSTM bidirectional long short-term memory network model respectively to obtain a first output result and a second output result; The first output result and the second output result are spliced ​​and processed and then input into a pre-built trajectory prediction model to obtain the predicted motion trend.

9. The method according to claim 1, characterized in that: The navigation and orientation control of the tunnel boring machine TBM according to the movement trend so that the tunnel boring machine TBM performs the tunneling task according to the predetermined tunneling route includes: Matching the movement trend with the excavation route to obtain excavation deviation related information of the roadheader TBM; A posture calibration instruction is generated according to the excavation deviation related information, and the posture calibration instruction is sent to the tunnel boring machine TBM, so that the tunnel boring machine TBM performs the excavation task along the excavation route according to the posture calibration instruction.

10. A navigation and orientation device for a tunnel boring machine (TBM), characterized in that: include: A data acquisition module is used to acquire a plurality of tunneling related parameters of a tunnel boring machine (TBM), wherein the tunneling related parameters include propulsion speed, penetration, cutter head thrust, cutter head rotation speed and cutter head torque; A data preprocessing module, used for preprocessing the plurality of tunneling related parameter data to obtain a plurality of preprocessed tunneling related parameters; A trend prediction module, used for extracting features in the time domain and frequency domain of the plurality of pre-processed tunneling related parameters, and determining the movement trend of the tunnel boring machine TBM within a predetermined time period in the future according to the extracted features; The navigation and orientation module is used to perform navigation and orientation control on the tunnel boring machine TBM according to the movement trend, so that the tunnel boring machine TBM performs the tunneling task according to the predetermined tunneling route.

11. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions, and the processor is used to execute the computer-readable instructions, wherein the computer-readable instructions execute the method according to any one of claims 1 to 9 when executed.

12. A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the method according to any one of claims 1 to 9.

Images