Shield tail deformation prediction method and device, equipment and readable storage medium

Abstract

The embodiment of the present application provides a shield tail deformation prediction method, device and equipment and a readable storage medium, wherein the shield tail deformation prediction method comprises the following steps: acquiring a distance change actual value of a detection mark point on an inner wall of a shield tail of a shield tunneling machine and at least one deformation amount of the detection mark point in a deformation state; establishing a change mapping model based on the detection mark point by a radial basis function neural network method according to the distance change actual value and the at least one deformation amount; and calculating a distance change prediction value of the detection mark point corresponding to the at least one deformation amount by the change mapping model. The present application also provides a shield tail deformation prediction device and equipment and a readable storage medium. Through the embodiment, the actual deformation amount can be monitored in real time and accurately, and the occurrence of situations such as misalignment of segment installation caused by collapse or deformation intrusion of the inner wall of the tunnel can be avoided.

Description

TECHNICAL FIELD

[0001] Embodiments herein relate to the technical field of tunnel construction equipment detection, in particular to a shield tail deformation prediction method, device, equipment and readable storage medium. BACKGROUND

[0002] The description in this section merely provides background information related to the disclosure of the embodiments herein and does not constitute prior art.

[0003] In the actual construction process of a shield, due to the special underground environment, the tunnel constructed by the shield machine is prone to be invaded by soil and rock, affected by high-pressure water, and also affected by the advancing speed of the shield machine, so that the shield tail is prone to deformation; in the actual process, the deformation is generally elliptical deformation, after the shield tail is deformed, it is difficult to form a ring when the tunnel is initially installed, which increases the difficulty of assembling the segments, or even leads to the problem of being unable to assemble, which seriously affects the normal construction quality and construction progress. Therefore, in the construction process of the shield machine, a series of methods are generally used to monitor the deformation of the shield tail, and then the deformed shield tail is timely corrected to avoid further invasion.

[0004] The existing monitoring means is relatively single, there is a monitoring system that uses a grating strain gauge to monitor the relative deformation, but this method cannot actually obtain accurate deformation with certain error and needs to stop work for measurement at any time, there is also a device that uses laser to measure the deformation distance, but in the actual construction process, the equipment is moved on the main beam at any time, which blocks the laser measurement, and cannot achieve the actual measurement effect; in addition, there are devices that use sliders, springs or tensioners for physical measurement, but the reliability of these devices is low, they are easy to be damaged in the tunnel construction process, and therefore the utilization rate is low.

[0005] It should be noted that the above introduction to the technical background is only to facilitate the clear and complete description of the technical scheme of the embodiments herein, and to facilitate the understanding of those skilled in the art. The above technical scheme cannot be considered as known to those skilled in the art merely because it is described in the background section of the embodiments herein. SUMMARY

[0006] The purpose of the embodiments herein is to provide a shield tail deformation prediction method, device, equipment and readable storage medium, which solves the problem of the need for high reliability and accurate monitoring of the deformation and distance change of the inner wall of the shield tail in the field of tunnel construction equipment detection.

[0007] The above implementation purposes of the embodiments herein are mainly realized by the following technical schemes:

[0008] On the one hand, the embodiments herein provide a shield tail deformation prediction method, comprising:

[0009] obtaining a distance change actual value of a detection mark point on an inner wall of a shield tail of a shield tunneling machine, and at least one deformation amount of the detection mark point in a deformed state;

[0010] establishing a change mapping model based on the detection mark point by a radial basis function neural network method according to the distance change actual value and the at least one deformation amount;

[0011] calculating a distance change predicted value of the detection mark point corresponding to the at least one deformation amount by the change mapping model.

[0012] In an embodiment, the method further comprises:

[0013] setting an error evaluation threshold, comparing an absolute value of a difference between the distance change predicted value and the distance change actual value with the error evaluation threshold according to the absolute value of the difference;

[0014] adjusting the change mapping model if the absolute value of the difference is greater than the error evaluation threshold.

[0015] In an embodiment, the change mapping model based on the detection mark point is established by the radial basis function neural network method according to the distance change actual value and the at least one deformation amount, comprising:

[0016] the at least one deformation amount comprises a first deformation amount along a tunnel axial direction and a second deformation amount along a tunnel circumferential direction;

[0017] determining a value of a Gaussian function of a hidden layer neural network according to the first deformation amount and the second deformation amount by using the Gaussian function as a radial basis function;

[0018] constructing the change mapping model based on the value of the Gaussian function, a weight coefficient corresponding to the first deformation amount, and a weight coefficient corresponding to the second deformation amount.

[0019] In an embodiment, the value of the Gaussian function of the hidden layer neural network is determined according to the first deformation amount and the second deformation amount by using the Gaussian function as the radial basis function, comprising:

[0020] setting a number of neurons of the hidden layer, and determining a center of each of the neurons by a clustering method;

[0021] calculating the value of the Gaussian function according to a Euclidean distance between the first deformation amount and the center of each of the neurons, and a Euclidean distance between the second deformation amount and the center of each of the neurons.

[0022] In an embodiment, the number of neurons of the hidden layer is set, the centers of each of the neurons are determined by a clustering method, comprising:

[0023] A vector space is established based on the number of neurons of the hidden layer, and an equal number of families is set;

[0024] The center of each of the families is calculated according to a K-means clustering algorithm;

[0025] The center of each of the families is taken as the center of each of the neurons of the hidden layer.

[0026] In an embodiment, the method further comprises:

[0027] Based on the plurality of actual distance change values and the plurality of predicted distance change values corresponding to the detection marker points, some of the predicted distance change values are replaced by some of the actual distance change values to form a distance change value data set of the detection marker points;

[0028] After removing the maximum value and the minimum value in the distance change value data set, the average value of the distance change values of the remaining distance change value data in the distance change value data set is calculated;

[0029] The average value of the distance change values is compared with a safe deformation range, and if the average value of the distance change values is greater than the safe deformation range, an alarm is output.

[0030] On the other hand, the embodiments also provide a tail deformation prediction device, comprising:

[0031] An acquisition unit acquires an actual distance change value of a detection marker point on an inner wall of a tail of a shield tunneling machine, and at least one deformation amount of the detection marker point in a deformation state;

[0032] A modeling unit establishes a change mapping model based on the detection marker point according to the actual distance change value and at least one deformation amount by a radial basis function neural network method;

[0033] A calculation unit calculates a predicted distance change value of the detection marker point corresponding to at least one deformation amount by the change mapping model.

[0034] In an embodiment, the device further comprises:

[0035] An error evaluation unit sets an error evaluation threshold, compares an absolute value of a difference between the predicted distance change value and the actual distance change value with the error evaluation threshold, and adjusts the change mapping model if the absolute value of the difference is greater than the error evaluation threshold.

[0036] In still another aspect, the embodiments herein also provide a computer device comprising a memory, a processor and a computer program stored on the memory and loadable on the processor, the processor implementing the shield tail deformation prediction method when executing the computer program.

[0037] Finally, the embodiments herein also provide a computer readable storage medium storing a computer program, the computer program implementing the shield tail deformation prediction method when executed by a processor.

[0038] Compared with the prior art, the technical solutions of the embodiments herein have the following characteristics and advantages:

[0039] 1. The embodiments herein can directly monitor the deformation amount and distance change value of the shield tail of the tunneling machine through the detection module, and in the case that the monitoring module is blocked, the distance change value data is obtained through the prediction method. The shield tail deformation detection method provided by the embodiments herein can avoid the situation that the distance deformation data cannot be obtained due to the direct monitoring field of the detection module being blocked by the assembly machine or the oil cylinder during the working process of the assembly machine or the tunneling process, and full-time direct data monitoring is achieved.

[0040] 2. The embodiments herein adopt two monitoring methods, and are directly loaded on the main beam and the inner wall of the shield tail, which avoids the influence of complex structures on the passing space of the shield tunneling machine, and adopts a double insurance monitoring method, which has high reliability and avoids the risk of monitoring mechanism failure caused by the complex underground tunnel construction environment. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments herein or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the embodiments herein, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0042] Figure 1 Flow chart of the shield tail deformation prediction method of the embodiments herein;

[0043] Figure 2 Flow chart of step S2 of the shield tail deformation prediction method of the embodiments herein;

[0044] Figure 3 Flow chart of step S22 of the shield tail deformation prediction method of the embodiments herein;

[0045] Figure 4 Flow chart of step S221 of the shield tail deformation prediction method of the embodiments herein;

[0046] Figure 5Flow chart of step S24 of the shield tail deformation prediction method of the embodiment of the present application;

[0047] Figure 6 Flow chart of step S4 of the shield tail deformation prediction method of the embodiment of the present application;

[0048] Figure 7 Module diagram of the shield tail deformation prediction device of the embodiment of the present application;

[0049] Figure 8 Schematic diagram of the shield tail deformation prediction device of the embodiment of the present application in a tunnel;

[0050] Figure 9 Structural schematic diagram of the laser range finder of the shield tail deformation prediction device of the embodiment of the present application;

[0051] Figure 10 Structural schematic diagram of the grating strain gauge of the shield tail deformation prediction device of the embodiment of the present application;

[0052] Figure 11 Structural schematic diagram of a computer device of the embodiment of the present application.

[0053] BRIEF DESCRIPTION OF THE DRAWINGS

[0054] 1, erector; 11, main beam;

[0055] 2, laser range finder; 21, adjusting mechanism; 211, fixing frame; 212, angle adjusting frame;

[0056] 3, grating strain gauge;

[0057] 4, detection mark point;

[0058] 5, computer device; 51, processor; 52, driving mechanism; 53, input / output module; 531, input device; 532, output device; 5321, presentation device; 5322, graphical user interface; 54, network interface; 541, communication link; 542, communication bus;

[0059] 6, memory;

[0060] F, axial direction;

[0061] Q, circumferential direction;

[0062] C i , center;

[0063] x, deformation amount;

[0064] x1, first deformation amount;

[0065] x2, second deformation amount;

[0066] σ, base function width;

[0067] X, central axis of the shield machine;

[0068] ΔL, distance change actual value;

[0069] ΔL y , distance change predicted value;

[0070] L, distance change actual value;

[0071] L y , distance change predicted value;

[0072] w1, weight coefficient of the first deformation amount;

[0073] w2, weight coefficient of the second deformation amount;

[0074] d, error evaluation value;

[0075] D, error evaluation threshold value;

[0076] ΔL p , distance change value average value;

[0077] L p , distance change value average value;

[0078] ΔL a , safe deformation range;

[0079] T, distance change value data group;

[0080] T1, distance change value data group. DETAILED DESCRIPTION

[0081] In order for those skilled in the art to better understand the technical solutions in the embodiments herein, the technical solutions in the embodiments herein will be clearly and completely described below with reference to the drawings in the embodiments herein. Obviously, the described embodiments are only part of the embodiments herein, rather than all the embodiments. Based on the embodiments in the embodiments herein, all other embodiments obtained by those of ordinary skill in the art without creative work should fall within the scope of protection of the embodiments herein.

[0082] It is to be understood that the terms "first", "second", and the like in the description and in the claims of this text are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of data in this text, if any, can be interchangeable in order to accomplish the same objectives, unless otherwise understood from the context. Moreover, the terms "comprising", "having", "including", and "containing" are to be construed open-ended terms (i.e., meaning "including, but not limited to") unless otherwise noted. As used herein, "exemplary" and "for example" mean "an example of." As used herein, "plurality" means "more than one."

[0083] It is to be understood that the steps illustrated in the attached drawings, which consist of blocks, can be carried out in computer systems such as a group of computers executing a set of computer-executable instructions, and that the illustrated ordering of these steps can sometimes be

[0084] As shown in Figure 1 is a flow chart of a shield tail deformation prediction method according to an embodiment of the present text, which can include:

[0085] Step S1: obtaining a distance change actual value AL of a detection marker point 4 on the inner wall of the shield tail of the shield tunneling machine, and at least one deformation amount x of the detection marker point 4 in a deformation state;

[0086] Step S2: according to the distance change actual value AL and the at least one deformation amount x, a change mapping model based on the detection marker point 4 is established by a radial basis function neural network method;

[0087] Step S3: the distance change predicted value AL of the detection marker point 4 corresponding to the at least one deformation amount x is calculated by the change mapping model y .

[0088] The shield tail deformation prediction method provided by the embodiments of the present text can monitor the deformation degree of the shield tail at any time during the tunneling process of the tunneling machine or during the process of assembling the segments by the segment assembling machine 1, and can associate the deformation degree with the actual deformation distance value corresponding to the deformation position. In the case that the monitoring field of view of the laser range finder 2 on the inner wall of the shield tail is blocked, the actual deformation distance value of the shield tail can be predicted according to the deformation degree of the shield tail, so as to realize real-time monitoring and early warning of the inner wall of the shield tail in the tunnel. When the distance change value exceeds the safe deformation range AL a , the shield tail deformation prediction method can issue a warning at any time, and can ensure the normal operation of the segment assembling machine 1 by cooperating with manual intervention.

[0089] In a feasible embodiment of the present text, please refer to Figure 8 andFigure 9 As shown in step S1: taking the center axis X of the shield tunneling machine as the horizontal coordinate baseline of the reference coordinate system, selecting a certain point on the center axis X as the monitoring origin, and setting the laser range finder 2 at the monitoring origin. In other embodiments, other distance measuring tools can also be used, which is not limited.

[0090] Correspondingly, in other embodiments herein, the laser range finder 2 can also be set at any convenient monitoring position on the shield tunneling machine, which needs to meet the condition that the laser range finder 2 has a direct measurement of the distance between the detection mark point 4, and the position is fixed relative to the detection mark point 4 on the inner wall of the shield tail of the shield tunneling machine.

[0091] In this embodiment, specifically, the main beam 11 of the assembling machine 1 is arranged along the center axis X of the shield tunneling machine, and the laser range finder 2 is installed on the main beam 11 of the assembling machine 1 through the adjusting mechanism 21. The adjusting mechanism 21 has a fixing frame 211 and an angle adjusting frame 212, and the adjusting mechanism 21 can adjust the ranging angle of the laser range finder 2 through the angle adjusting frame 212, so that the ranging angle of the laser range finder 2 corresponds to the detection mark point 4 on the inner wall of the shield tail of the tunnel. The laser range finder 2 measures the distance between the detection mark point 4 at a certain frequency, and obtains the actual distance change value ΔL between the detection mark point 4 and the laser range finder 2. In this embodiment, the actual distance change value ΔL is the absolute value of the difference between the distance between the detection mark point 4 measured by the laser range finder 2 at the present moment and the distance between the detection mark point 4 measured by the laser range finder 2 at the initial moment. In another embodiment, the actual distance change value L is the distance between the detection mark point 4 measured by the laser range finder 2 at the present moment. In other embodiments, the actual distance change value L can also be set as other distance values related to the distance change of the detection mark point 4, which is not limited.

[0092] Further, in combination with the above-mentioned Figure 10As shown, the shield tail inner wall of the shield tunneling machine is further provided with a grating strain gauge 3, and the deformation degree is displayed by measuring the voltage signal on the grating strain gauge 3, but in other embodiments, other deformation detection devices can also be used, and the deformation degree can be revealed by measuring the change of resistance, measuring the change of current or measuring the change of stress, which is not limited herein; wherein, at least one grating strain gauge 3 is arranged at the detection mark point 4, when a plurality of grating strain gauges 3 are used for detection, the grating strain gauges 3 are arranged along the axial direction F of the tunnel (i.e. the direction of the central axis X of the shield tunneling machine) and the circumferential direction Q of the tunnel, and in other embodiments, the grating strain gauges 3 can also be arranged along the direction of the tunnel which is easy to deform; specifically, in the embodiment, two grating strain gauges 3 are arranged along the axial direction F of the tunnel and the circumferential direction Q of the tunnel respectively, the two grating strain gauges 3 are both connected with a Wheatstone half-bridge detection circuit, and the two grating strain gauges 3 and the laser range finder 2 perform measurement work at the same frequency at the same time, when the shield tail deforms, the detection output voltage signal of the grating strain gauges 3 is collected by the collection module, and the first deformation amount x1 and the second deformation amount x2 of the detection mark point 4 in the deformed state are obtained.

[0093] As shown in Figures 2 to 4 In step S2, a change mapping model based on the detection mark point 4 is established by a radial basis function neural network method according to the distance change actual value AL and at least one deformation amount x, and in the embodiment, the change mapping model mainly includes:

[0094] Step S21: the at least one deformation amount x includes a first deformation amount x1 along the axial direction F of the tunnel and a second deformation amount x2 along the circumferential direction Q of the tunnel;

[0095] Step S22: according to the first deformation amount x1 and the second deformation amount x2, a Gaussian function is used as a radial basis function to determine the value of the Gaussian function of the hidden layer neural network;

[0096] Step S23: based on the value of the Gaussian function, the weight coefficient corresponding to the first deformation amount x1, and the weight coefficient corresponding to the second deformation amount x2, the change mapping model is constructed.

[0097] Specifically, by the radial basis function neural network method, a change mapping model based on the detection mark point 4 is established, mainly to establish a corresponding relationship between the first deformation amount x1 along the axial direction F of the tunnel obtained by the grating strain gauge 3 and the second deformation amount x2 along the circumferential direction Q of the tunnel and the distance change actual value AL of the detection mark point 4 measured by the laser range finder 2, that is, the change mapping model. In another embodiment, that is, the first deformation amount x1, the second deformation amount x2 and the distance change actual value L are established corresponding relationship; the embodiment adopts RBF radial basis function (RADIAL BASIS FUNCTION, RBF) neural network, and in other embodiments, other similar neural network methods can also be used, which are not limited here.

[0098] As shown in Figure 3 , in step S22, according to the first deformation amount x1 and the second deformation amount x2, the Gaussian function is used as the radial basis function to determine the value of the Gaussian function of the hidden layer neural network, including:

[0099] Step S221: Set the number of neurons in the hidden layer, and determine the center C i of each neuron by clustering method.

[0100] Step S222: According to the Euclidean distance between the first deformation amount x1 and the center C i of each neuron, and the Euclidean distance between the second deformation amount x2 and the center C i of each neuron, the value of the Gaussian function is calculated.

[0101] Specifically, as shown in Figure 4 , the Gaussian function value of the first deformation amount x1 and the second deformation amount x2 is required, as described in step S221, first the center C i of a plurality of neurons needs to be calculated according to the clustering algorithm. In an available embodiment of the present application, the clustering algorithm includes:

[0102] Step S2211: Based on the number of neurons in the hidden layer, a vector space is established and an equal number of families are set;

[0103] Step S2212: According to the K-means clustering algorithm, the center of each family is calculated;

[0104] Step S2213: The center of each family is taken as the center C i of each neuron in the hidden layer.

[0105] In this embodiment, the number of neurons in the hidden layer and the distance change prediction value AL yThe number of neurons in the hidden layer can be set according to requirements, and in the vector space, an equal number of families can be established according to the number of neurons in the hidden layer set, and the average value of sample points in each family can be calculated by the K-means clustering algorithm, wherein the average value of sample points in each family is the center point of each family. In other embodiments, a hierarchical clustering algorithm or the like can also be used, which is not limited herein.

[0106] Further, as step S222, the Euclidean distance between the first deformation amount x1 and the center C i of each neuron and the Euclidean distance between the second deformation amount x2 and the center C i of each neuron need to be calculated according to the number of neurons set, and the values of the Gaussian function corresponding to the first deformation amount x1 and the second deformation amount x2 are calculated according to the Euclidean distance between the first deformation amount x1 and the center C i of each neuron and the Euclidean distance between the second deformation amount x2 and the center C i of each neuron, respectively, and the specific calculation is as follows:

[0107] The Euclidean distance between the first deformation amount x1 and the center C i of each neuron is:

[0108] ‖x1-C i ‖i=1,2...n

[0109] The Euclidean distance between the second deformation amount x2 and the center C i of each neuron is:

[0110] ‖x2-C i ‖i=1,2...n

[0111] Wherein, i is the number of neurons in the hidden layer set, and C i is the center of the neuron in the hidden layer.

[0112] Further, in step S222, the values of the Gaussian function corresponding to the first deformation amount x1 and the second deformation amount x2 are calculated according to the Euclidean distance between the first deformation amount x1 and the center C i of each neuron and the Euclidean distance between the second deformation amount x2 and the center C i of each neuron, respectively, and the specific calculation is as follows:

[0113]

[0114]

[0115] Wherein, i is the number of neurons in the hidden layer set, and σ is the width of the base function (i.e., the smoothing factor controlling the smoothness of the Gaussian function).

[0116] In step S23, as Figure 2As shown, based on the value of the Gaussian function of the first deformation amount x1, the value of the Gaussian function of the second deformation amount x2, the weight coefficient w1 of the first deformation amount x1, and the weight coefficient w2 of the second deformation amount x2, the distance change prediction value ΔL y , that is, the constructed change mapping model is as follows:

[0117]

[0118] The weight coefficient w1 of the first deformation amount x1 and the weight coefficient w2 of the second deformation amount x2 are set according to the deformation degree in the respective direction, and the sum of the weight coefficient w1 of the first deformation amount x1 and the weight coefficient w2 of the second deformation amount x2 is 1. For reference, when multiple deformation amount data x n are input, the corresponding distance change prediction value ΔL y can be calculated by the change mapping model. Similarly, in the embodiment, the distance change prediction value ΔL y is the absolute value of the difference between the predicted distance between the laser range finder 2 and the detection marker point 4 at the current time and the distance between the laser range finder 2 and the detection marker point 4 measured at the initial time. In another embodiment, the distance change prediction value ΔL y is the predicted distance between the laser range finder 2 and the detection marker point 4 at the current time. In other embodiments, the distance change prediction value ΔL y may also be other distance prediction values related to the distance change of the detection marker point 4 corresponding to other set distance change actual values ΔL, and the present disclosure is not limited thereto,

[0119] As shown in Figure 5 , based on step S2, in an available embodiment of the present disclosure, the shield tail deformation prediction method further includes adjusting the change mapping model, including:

[0120] Step S241: Set an error evaluation threshold D, and compare the absolute value of the difference between the distance change prediction value ΔL y and the distance change actual value ΔL with the error evaluation threshold D.

[0121] Step S242: If the absolute value of the difference is greater than the error evaluation threshold D, adjust the change mapping model.

[0122] Specifically, in the embodiment, when the measurement field of the laser range finder 2 and the detection marker point 4 is not blocked, the distance change actual value ΔL can be obtained, and then the distance change actual value ΔL is compared with the calculated distance change prediction value ΔL yThe absolute values ​​of the differences are compared and filtered to evaluate whether the established change mapping model is qualified. If it is not qualified, steps S22 to S23 are repeated. In step S241 of this embodiment, the distance change prediction value ΔL is used as the basis for the evaluation. y The absolute value of the difference between the error evaluation value d and the actual distance change ΔL is used to calculate the error evaluation value d. The specific formula for calculating the error evaluation value d is as follows:

[0123]

[0124] When d is greater than D, steps S22 to S23 are repeated; when d is less than or equal to D, the predicted distance change value ΔL is output. y ;

[0125] In another embodiment, when the measurement field of view of the laser rangefinder 2 and the detection marker 4 is unobstructed, the actual value of the distance change L can be obtained, and then the actual value of the distance change L can be compared with the calculated predicted value of the distance change L. y The absolute values ​​of the differences are compared and filtered to evaluate whether the established change mapping model is qualified. Meanwhile, in step S241 of another embodiment, the distance change prediction value L is used... y The formula for calculating the error evaluation value d is as follows: (The absolute value of the difference between the actual distance change L and the actual distance change L.)

[0126]

[0127] Specifically, when d is greater than D, steps S22 to S23 are repeated; when d is less than or equal to D, the predicted distance change value L is output. y .

[0128] like Figure 6 As shown, in steps S1 to S3, a feasible embodiment of this paper further includes monitoring and issuing early warnings for the actual value ΔL of the distance change, including:

[0129] Step S41: Based on the actual distance change values ​​ΔL and the predicted distance change values ​​ΔL corresponding to the detection marker point 4 y The predicted value of partial distance change ΔL y Replace part of the actual distance change value ΔL to form the distance change value data group T1 for the detection marker point 4;

[0130] Step S42: After removing the maximum and minimum values ​​from the distance change value data group T1, calculate the average distance change value ΔL of the remaining distance change value data in the distance change value data group T1. p ;

[0131] Step S43: Compare the average distance change value ΔL pwith the safe deformation range AL a , if the distance change value average AL p is greater than the safe deformation range AL a , an alarm is output.

[0132] Specifically, to achieve the effect of early warning of the deformation degree of the shield tail, first, the distance change actual value AL of the detection marker point 4 is compared with the safe deformation range AL a , as step S41, the distance change value data set T is established according to the obtained distance change actual value AL, as follows:

[0133] T = [AL1, AL2, AL3... AL n ]

[0134] Wherein, AL1... AL n is the distance change actual value AL obtained by the laser range finder 2, n is the capacity of the distance change value data set T, and the distance change value data set T collects the distance change actual values AL1... AL n obtained in the last n times;

[0135] Further, in the process of obtaining the distance change actual value AL by the laser range finder 2, the view may be blocked by the moving equipment, etc., at this time, the corresponding distance change predicted value AL y calculated by the change mapping model is used to replace the original blocked distance change actual value AL to form a new distance change value data set T1, in one specific embodiment of the embodiment, the updated distance change value data set T1 is as follows:

[0136] T1 = [AL1, AL y2 , AL y3 , AL4... AL n ]

[0137] As step S42, to obtain stable distance change value data, the distance change value data set T1 obtained in the last n times needs to be filtered in advance, that is, the maximum value and the minimum value in the distance change value data set T1 are removed and the distance change value average AL p of the remaining data is calculated, as follows:

[0138]

[0139] Wherein, the distance change value average AL p of the detection marker point 4 is compared with the safe deformation range AL a , when AL p is greater than AL a , the warning information is output; when ALp less than or equal to AL a The safety information is outputted. Based on the monitoring and warning method of the actual distance change value AL, steps S41 to S43 are repeatedly executed in each time the laser range finder 2 measures the actual distance change value AL and the grating strain gauge 3 measures the deformation amount x. The measurement frequency of the laser range finder 2 and the grating strain gauge 3 determines the accuracy of the shield tail deformation condition monitoring. Therefore, in the above embodiment, the specifications of the laser range finder 2 and the grating strain gauge 3 are at least 12 times or more per hour, and the measurement frequency can be adjusted according to the accuracy and progress required by the actual construction.

[0140] In another embodiment, the actual distance change value L is monitored and warned, including:

[0141] Step S41: Based on the plurality of actual distance change values L and the plurality of distance change prediction values L corresponding to the detection marker point 4 y , some distance change prediction values L y are replaced by some actual distance change values L to form a distance change value data set T1 of the detection marker point 4.

[0142] Step S42: After removing the maximum value and the minimum value in the distance change value data set T1, the average distance change value L of the remaining distance change value data in the distance change value data set T1 is calculated. p

[0143] Step S43: Compare the average distance change value L p with the safe deformation range AL a , if the average distance change value L p is greater than the safe deformation range AL a , output an alarm.

[0144] The distance change value data set T in the other embodiment is:

[0145] T = [L1, L2, L3...L n ]

[0146] An embodiment of the updated distance change value data set T1 in the other embodiment is:

[0147] T1 = [L1, L y2 , L y3 , L4...L n ]

[0148] In the other embodiment, the specific formula for removing the maximum value and the minimum value in the distance change value data set T1 and calculating the average distance change value L p of the remaining data is as follows: ​

[0149]

[0150] wherein the safety deformation range ΔL a is a range of the set safety distance between the laser range finder 2 and the detection mark point 4, and the average value L p of the distance change value of the detection mark point 4 is compared with the safety deformation range ΔL a , when L p is outside the range of ΔL a , the warning information is outputted; when ΔL p is within the range of ΔL a , the safety information is outputted. In other embodiments, the specific monitoring and warning process of the method can be replaced by conventional means according to the set distance mode.

[0151] Based on the same inventive concept, as shown in Figure 7 , Figure 8 , the present embodiment also provides a shield tail deformation prediction device, as in the above embodiment, specifically comprising:

[0152] an acquisition unit, which acquires the distance change actual value ΔL of the detection mark point 4 on the inner wall of the shield tail of the shield tunneling machine, and at least one deformation amount x of the detection mark point 4 in the deformation state;

[0153] a modeling unit, which establishes a change mapping model based on the detection mark point 4 according to the distance change actual value ΔL and the at least one deformation amount x through a radial basis function neural network method;

[0154] a calculation unit, which calculates the distance change predicted value ΔL y

[0155] The shield tail deformation prediction device provided by the present embodiment can monitor the deformation degree of the shield tail at any time during the tunneling process of the tunneling machine or the process of assembling the segments by the assembling machine 1, and associate the deformation degree with the actual deformation distance corresponding to the deformation position. In the case that the monitoring field of view of the laser monitor on the inner wall of the shield tail is blocked, the actual deformation distance of the shield tail can be predicted according to the deformation degree of the shield tail, so as to realize real-time monitoring and early warning of the inner wall of the shield tail in the tunnel. When the actual deformation distance exceeds the safety deformation range ΔL a , the shield tail deformation prediction method can issue a warning at any time, and cooperate with manual intervention to ensure the normal operation of the assembling machine.

[0156] Further, the shield tail deformation prediction device provided by the present embodiment further comprises:

[0157] The error evaluation unit sets an error evaluation threshold D, and evaluates the distance change prediction value ΔL according to the distance change actual value ΔL y The difference absolute value between the distance change prediction value ΔL and the distance change actual value ΔL, compares the difference absolute value with the error evaluation threshold D; wherein, if the difference absolute value is greater than the error evaluation threshold D, the change mapping model is adjusted.

[0158] The error evaluation unit can evaluate the established change mapping model, and timely improve the accuracy of the change mapping model, so that the distance change prediction value ΔL calculated by the change mapping model is more accurate. y The accuracy is higher, and the actual deformation distance of the shield tail is more effectively monitored, so that the situation that the tunnel deformation invades the tunneling machine or invades the segment installation area, which leads to the failure of the segment installation, is avoided.

[0159] Since the principle of solving the problem of the device is similar to the shield tail deformation prediction, the implementation of the device can refer to the implementation of the shield tail deformation prediction method, and the repeated parts will not be repeated.

[0160] As Figure 11 The structure of the computer device provided by the embodiment of the present application is shown in the figure. The computer device in the embodiment of the present application can complete the shield tail deformation prediction method described above. The computer device 5 can include one or more processors 51, such as one or more central processing units (CPU), each of which can implement one or more hardware threads. The computer device 5 can also include any memory 6 for storing any kind of information such as code, settings, data, etc. Non-limiting, for example, the memory 6 can include any one or a combination of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any memory can store information using any technology. Further, any memory can provide volatile or non-volatile retention of information. Further, any memory can represent a fixed or removable component of the computer device 5. In one case, the computer device 5 can perform any operation of the associated instructions when the processor 51 executes the associated instructions stored in any memory or combination of memories. The computer device 5 also includes one or more drive mechanisms 52 for interacting with any memory, such as a hard disk drive mechanism, an optical disk drive mechanism, etc.

[0161] Computer device 5 may also include an input / output module 53 (I / O) for receiving various inputs (via input device 531) and providing various outputs (via output device 532). A specific output mechanism may include a presentation device 5321 and an associated graphical user interface 5322 (GUI). In other embodiments, the input / output module 53 (I / O), input device 531, and output device 532 may be omitted, and the device may function solely as a computer device within a network. Computer device 5 may also include one or more network interfaces 54 for exchanging data with other devices via one or more communication links 541. One or more communication buses 542 couple the components described above together.

[0162] Communication link 541 can be implemented in any way, such as via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, or any combination thereof. Communication link 541 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0163] correspond Figures 1 to 6 In addition to the method described above, this embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described shield tail deformation prediction method.

[0164] correspond Figures 1 to 6 In addition to the method described above, this embodiment also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described shield tail deformation prediction method.

[0165] It should be understood that in the various embodiments of this document, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this document.

[0166] It should also be understood that, in the embodiments herein, the term "and / or" is merely a description of the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following associated objects have an "or" relationship.

[0167] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0168] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0169] In several embodiments provided herein, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are merely schematic, for example, the division of units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can also be electrical, mechanical or other form of connection.

[0170] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments provided herein.

[0171] In addition, each functional unit in each embodiment herein can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0172] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions herein or the entire or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the various embodiments of the method. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0173] The principles and implementation manners of the present application are described in the specific embodiments herein, and the above descriptions of the embodiments are only used to help understand the method and the core idea thereof; meanwhile, for those skilled in the art, the specific implementation manners and application ranges can be changed according to the idea of the present application, and the above descriptions of the present application should not be understood as limitations.

Claims

1. A method of predicting a tail shield deformation, characterized by, The method comprises: acquiring a distance change actual value of a detection mark point on an inner wall of a shield tail of a shield tunneling machine, and at least one deformation amount of the detection mark point in a deformed state; wherein a laser range finder is installed on a main beam of the shield tunneling machine through an adjusting mechanism, the adjusting mechanism has a fixing frame and an angle adjusting frame, the adjusting mechanism adjusts a distance measuring angle of the laser range finder through the angle adjusting frame, and the distance measuring angle of the laser range finder is used to acquire the distance change actual value between the detection mark point on the inner wall of the shield tail and the laser range finder; a change mapping model based on the detection mark point is established through a radial basis function neural network method according to the distance change actual value and the at least one deformation amount; the at least one deformation amount includes a first deformation amount in an axial direction of a tunnel and a second deformation amount in a circumferential direction of the tunnel; two grating strain gauges are arranged on the inner wall of the shield tail along the axial direction of the tunnel and the circumferential direction of the tunnel respectively, the two grating strain gauges and the laser range finder perform measurement work at the same frequency at the same time, and the first deformation amount and the second deformation amount of the detection mark point in the deformed state are acquired when the shield tail is deformed; a Gaussian function is used as a radial basis function to determine the value of the Gaussian function of a hidden layer neural network according to the first deformation amount and the second deformation amount; the number of neurons of the hidden layer is set, and the centers of the neurons are determined through a clustering method; a vector space is established and an equal number of families are set based on the number of neurons of the hidden layer; the centers of the families are calculated according to a K-means clustering algorithm; and the centers of the families are used as the centers of the neurons of the hidden layer; the value of the Gaussian function is calculated according to the Euclidean distance between the first deformation amount and the center of each neuron and the Euclidean distance between the second deformation amount and the center of each neuron; the change mapping model is constructed based on the value of the Gaussian function, a weight coefficient corresponding to the first deformation amount, and a weight coefficient corresponding to the second deformation amount; the distance change prediction value of the detection mark point corresponding to the at least one deformation amount is calculated through the change mapping model.

2. The shield tail deformation prediction method according to claim 1, characterized by, The method further comprises: an error evaluation threshold value is set, and the difference absolute value between the distance change prediction value and the distance change actual value is compared with the error evaluation threshold value; if the difference absolute value is greater than the error evaluation threshold value, the change mapping model is adjusted.

3. The shield tail deformation prediction method according to claim 1 or 2, characterized by, The method further comprises: a distance change value data group of the detection mark point is formed by replacing part of the distance change actual values with part of the distance change prediction values based on a plurality of distance change actual values and a plurality of distance change prediction values corresponding to the detection mark point; after removing the maximum value and the minimum value in the distance change value data group, the distance change value average of the remaining distance change value data in the distance change value data group is calculated. The distance change value average is compared with a safe deformation range, and if the distance change value average is greater than the safe deformation range, an alarm is output.

4. A shield tail deformation prediction device for implementing the shield tail deformation prediction method according to any one of claims 1 to 3, characterized by, The tail deformation prediction device comprises: An acquisition unit acquires a distance change actual value of a detection mark point on an inner wall of a tail of a shield tunneling machine and at least one deformation amount of the detection mark point in a deformation state; A modeling unit establishes a change mapping model based on the detection mark point by a radial basis function neural network method according to the distance change actual value and the at least one deformation amount; A calculation unit calculates a distance change prediction value of the detection mark point corresponding to the at least one deformation amount by the change mapping model.

5. The shield tail deformation prediction device according to claim 4, characterized by, Further comprising: An error evaluation unit sets an error evaluation threshold value, compares an absolute value of a difference between the distance change prediction value and the distance change actual value with the error evaluation threshold value, and adjusts the change mapping model if the absolute value of the difference is greater than the error evaluation threshold value.

6. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the tail deformation prediction method in any one of claims 1 to 3.

7. A computer readable storage medium characterized by The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the tail deformation prediction method in any one of claims 1 to 3.

Images