Synchronous grouting control method, device, equipment, medium and product

Abstract

The invention provides a synchronous grouting control method, device and equipment, a medium and a product, and relates to the field of shield construction. Comprising the steps of collecting real-time data; preprocessing the real-time data to obtain a real-time data set; determining a grouting filling coefficient according to the first real-time data subset and a preset grouting filling coefficient model; according to the second real-time data subset and the grouting filling coefficient, the theoretical grouting amount is determined; according to the third real-time data subset, the actual grouting amount is determined; and according to the real-time data set, the theoretical grouting amount and the actual grouting amount, a proportional-integral-differential control model is adjusted through an error back propagation neural network model, and a propulsion speed control instruction is generated. The technical problem that the synchronous grouting control efficiency is low due to the fact that the accuracy of synchronous grouting amount calculation and the adaptability of grouting pump speed control are insufficient in the prior art is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of shield construction, and in particular to a synchronous grouting control method, device, equipment, medium and product. BACKGROUND

[0002] Shield tunnel technology has become the preferred method for urban traffic tunnel construction due to its fast construction speed, small environmental impact, and high degree of mechanization. Shield construction is mainly carried out in urban areas, and the control of ground settlement is highly required. Synchronous grouting, as an important subsystem of the shield machine, fills cement slurry into the gap behind the tunnel lining segment wall during shield tunneling, which plays an important role in controlling ground settlement. Therefore, the control of synchronous grouting for shield is more stringent, and the grouting amount must be accurately and uniformly controlled.

[0003] Currently, the synchronous grouting system mainly adopts a control mode that gives priority to grouting amount and supplements with grouting pressure. First, the technical personnel determines the synchronous grouting filling coefficient according to the actual working conditions, and then obtains the synchronous grouting amount through theoretical calculation. In the actual grouting process, the number of strokes of the grouting pump is controlled according to the shield advancing speed, and the upper and lower limits of the grouting pressure are set to ensure that the grout can overcome the resistance and be injected quantitatively into the gap behind the tunnel lining segment wall.

[0004] However, the existing technology has deficiencies in the accuracy of synchronous grouting amount calculation and the adaptability of grouting pump speed control, resulting in low efficiency of synchronous grouting control. SUMMARY

[0005] The present application provides a synchronous grouting control method, device, equipment, medium and product to solve the problem of low efficiency of synchronous grouting control due to the deficiencies of the existing technology in the accuracy of synchronous grouting amount calculation and the adaptability of grouting pump speed control.

[0006] In a first aspect, the present application provides a synchronous grouting control method, comprising:

[0007] collecting real-time data;

[0008] preprocessing the real-time data to obtain a real-time data set; wherein the real-time data set includes a first real-time data subset, a second real-time data subset and a third real-time data subset;

[0009] determining a synchronous grouting filling coefficient according to the first real-time data subset and a preset synchronous grouting filling coefficient model;

[0010] determining a theoretical grouting amount according to the second real-time data subset and the synchronous grouting filling coefficient;

[0011] determining an actual grouting amount according to the third real-time data subset;

[0012] According to the real-time data set, the theoretical grouting amount and the actual grouting amount, the original proportional-integral-derivative control model is adjusted through the error back propagation neural network model to obtain an adjusted proportional-integral-derivative control model.

[0013] The application relates to the field of shield construction, and in particular to a synchronous grouting control method, device, equipment, medium and product.

[0014] The theoretical grouting amount and the actual grouting amount are input into the adjusted proportional-integral-derivative control model, so that a pushing speed control instruction is generated through the output result of the adjusted proportional-integral-derivative control model.

[0015] In a possible design, before the real-time data is preprocessed to obtain the real-time data set, the method further includes:

[0016] The historical data are acquired, a plurality of data samples in units of rings are generated, and a data sample set is obtained;

[0017] The data sample set is normalized to be converted into a dimensionless value set;

[0018] The synchronous grouting filling coefficient model is constructed according to the dimensionless value set.

[0019] In a possible design, after the synchronous grouting filling coefficient model is constructed according to the dimensionless value set, the method further includes:

[0020] The synchronous grouting filling coefficient model is solved according to the dimensionless value set and a least square method to obtain a model parameter solution set, wherein the model parameter solution set includes a plurality of model parameter solutions, and each model parameter solution corresponds to an influence parameter.

[0021] According to the model parameter solution and a preset error threshold, the reliability of the model parameter solution is judged.

[0022] If the model parameter solution in the model parameter solution set is not reliable, the model parameter solution is adjusted according to a preset adjustment strategy.

[0023] If all the model parameter solutions in the model parameter solution set are reliable, the synchronous grouting filling coefficient model is saved.

[0024] In a possible design, the second real-time data subset includes a first diameter of the shield machine, a second diameter of the shield machine and a shield machine pushing data set.

[0025] The theoretical grouting amount is determined according to the second real-time data subset and the synchronous grouting filling coefficient, and the method includes:

[0026] The synchronous grouting filling sectional area is calculated according to the first diameter of the shield machine and the second diameter of the shield machine.

[0027] According to the synchronous grouting filling section area, the shield machine advancing data set and the synchronous grouting filling coefficient, a theoretical grouting amount is calculated.

[0028] In a possible design, the third real-time data subset includes laser ranging historical data, laser ranging original data and tank data set.

[0029] The laser ranging original data includes first original data and second original data, and the first original data and the second original data are collected by independent first sensors and second sensors respectively.

[0030] According to the third real-time data subset, an actual grouting amount is determined, including:

[0031] The first original data and the second original data are respectively filtered by a median filtering algorithm to obtain first data and second data.

[0032] Whether the first data and the second data are disturbed during collection is determined by an abnormality detection strategy.

[0033] If disturbed, the laser ranging original data is re-collected according to the abnormality detection strategy processing.

[0034] If not disturbed, the actual grouting amount is calculated according to the tank data set, the laser ranging historical data, the first data and the second data.

[0035] In a possible design, the error back propagation neural network model includes an input layer, a hidden layer, a feedback layer and an output layer.

[0036] According to the real-time data set, the theoretical grouting amount and the actual grouting amount, the original proportional-integral-derivative control model is adjusted by the error back propagation neural network model to obtain an adjusted proportional-integral-derivative control model, including:

[0037] According to the real-time data set, the theoretical grouting amount, the actual grouting amount and the weight parameter set, an input layer output value and a feedback layer output value are obtained.

[0038] The input layer output value and the feedback layer output value are added to obtain a hidden layer input value.

[0039] According to the hidden layer input value and the weight parameter set, an output layer output value set is obtained.

[0040] The original proportional-integral-derivative control model is adjusted according to the output layer output value set to obtain the adjusted proportional-integral-derivative control model.

[0041] In a possible design, the weight parameter set is automatically updated and adjusted by a cost function.

[0042] The weight parameter set is also revised by a gradient descent method.

[0043] In a second aspect, the application provides a synchronous grouting control device, comprising:

[0044] The acquisition module is configured to acquire real-time data.

[0045] The preprocessing module is configured to preprocess the real-time data to obtain a real-time data set.

[0046] The first determining module is configured to determine a synchronous grouting filling coefficient according to the first real-time data subset and a preset synchronous grouting filling coefficient model.

[0047] The second determining module is configured to determine a theoretical grouting amount according to the second real-time data subset and the synchronous grouting filling coefficient.

[0048] The third determining module is configured to determine an actual grouting amount according to the third real-time data subset.

[0049] The adjusting module is configured to adjust an original proportional-integral-derivative control model by an error back propagation neural network model according to the real-time data set, the theoretical grouting amount and the actual grouting amount, to obtain an adjusted proportional-integral-derivative control model.

[0050] The generating module is configured to input the theoretical grouting amount and the actual grouting amount into the adjusted proportional-integral-derivative control model, to generate a propelling speed control instruction by an output result of the adjusted proportional-integral-derivative control model.

[0051] In a third aspect, the application provides a synchronous grouting control device, comprising a memory and a processor.

[0052] The memory stores computer execution instructions.

[0053] The processor executes the computer execution instructions stored in the memory, so that the processor executes the synchronous grouting control method according to the first aspect.

[0054] In a fourth aspect, the application provides a computer readable storage medium, which stores computer execution instructions, and the computer execution instructions are used to implement the synchronous grouting control method according to the first aspect when executed by a processor.

[0055] In a fifth aspect, the application provides a computer program product, which comprises a computer program, and the computer program is used to implement the synchronous grouting control method according to the first aspect when executed by a processor.

[0056] The application provides a synchronous grouting control method, device, equipment, medium and product, which comprises the following steps: collecting real-time data; preprocessing the real-time data to obtain a real-time data set; determining a synchronous grouting filling coefficient according to a first real-time data subset and a preset synchronous grouting filling coefficient model; determining a theoretical grouting amount according to a second real-time data subset and the synchronous grouting filling coefficient; determining an actual grouting amount according to a third real-time data subset; adjusting an original proportional-integral-derivative control model through an error back propagation neural network model according to the real-time data set, the theoretical grouting amount and the actual grouting amount, so as to obtain an adjusted proportional-integral-derivative control model; and inputting the theoretical grouting amount and the actual grouting amount into the adjusted proportional-integral-derivative control model, so as to generate a propelling speed control instruction through an output result of the adjusted proportional-integral-derivative control model. Compared with the prior art, the application has the following advantages: the synchronous grouting filling coefficient mathematical model is established by using the historical data of the shield tunnel, the internal relationship between the synchronous grouting filling coefficient, the influencing factors and the ground settlement data is mined, the calculation of the synchronous grouting filling coefficient is more accurate, the back propagation neural network (BP neural network) adaptive proportional-integral-derivative control algorithm (PID control algorithm) with feedback is adopted, the PID control parameters can be dynamically adjusted according to the change of the propelling speed, the adaptability of the grouting speed control is improved, the liquid level of the grout tank is monitored by using the laser range finder, the actual grouting amount calculated is more accurate, and the synchronous grouting control efficiency is improved. BRIEF DESCRIPTION OF DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application 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 some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0058] Figure 1 A system architecture schematic diagram of a synchronous grouting control method provided by the embodiments of the present application;

[0059] Figure 2 A synchronous grouting control method flowchart provided by the embodiments of the present application Figure 1 ;

[0060] Figure 3A shield machine synchronous grouting control system structure schematic diagram provided by the embodiment of the application is shown in the figure.

[0061] Figure 4 A synchronous grouting control method flow process schematic diagram provided by the embodiment of the application is shown in the figure. Figure 2

[0062] Figure 5 A shield machine synchronous grouting filling coefficient model construction and identification module structure schematic diagram provided by the embodiment of the application is shown in the figure.

[0063] Figure 6 A synchronous grouting control method flow process schematic diagram provided by the embodiment of the application is shown in the figure. Figure 3

[0064] Figure 7 A BP neural network adaptive incremental PID grouting speed control structure schematic diagram provided by the embodiment of the application is shown in the figure.

[0065] Figure 8 A synchronous grouting control device structure schematic diagram provided by the embodiment of the application is shown in the figure.

[0066] Figure 9 A synchronous grouting control device structure schematic diagram provided by the embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0067] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The following description is made with reference to the accompanying drawings in which like reference numerals refer to like elements in the several figures. The following description of exemplary embodiments is not representative of all embodiments consistent with the present application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0068] In the embodiments of the present application, the same items or similar items with basically the same functions and effects are distinguished by using "first", "second", etc. The skilled in the art can understand that "first", "second", etc. do not limit the quantity and execution order, and "first", "second", etc. do not necessarily mean different. It should be noted that in the embodiments of the present application, "exemplary" or "for example" is used to represent as an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, "exemplary" or "for example" is used to present the relevant concept in a specific way. In the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more.

[0069] ​​It should be noted that the "at" in the embodiments of the present application can be the moment when a certain condition occurs, or a period of time after a certain condition occurs, and the embodiments of the present application do not make specific limitations. In addition, the synchronous grouting control method provided by the embodiments of the present application is only as an example, and the synchronous grouting control method can also include more or less content.

[0070] In order to clearly describe the technical solutions of the embodiments of the present application, the following briefly introduces some terms and technologies involved in the embodiments of the present application:

[0071] Backpropagation neural network (BP neural network): a kind of multilayer feedforward neural network trained by backpropagation algorithm, which belongs to supervised learning algorithm and is widely used in pattern recognition, function approximation and other fields.

[0072] Proportional-integral-derivative control algorithm (PID control algorithm): a kind of feedback control algorithm widely used in industrial control field, which realizes accurate control of system through combination of proportional, integral and differential three links.

[0073] Shield tunnel technology has become the first choice for urban traffic tunnel construction method with the advantages of fast construction speed, small environmental impact and high degree of mechanization. Shield construction is mainly carried out in urban areas, and the control of ground settlement is required.

[0074] Among them, synchronous grouting as an important subsystem of shield machine fills cement slurry into the gap behind the tunnel lining segment wall during shield tunneling, which plays an important role in controlling ground settlement. Therefore, the control of synchronous grouting of shield is more strict, and the grouting amount must be accurately and uniformly controlled.

[0075] Early synchronous grouting of shield takes setting grouting pressure as control target, but it is difficult to judge whether grouting is sufficient according to single grouting pressure, which may cause large deviation and uneven grouting. At present, the synchronous grouting system mainly adopts the control mode of taking grouting amount as the main and grouting pressure as the auxiliary. First, the technical personnel determine the synchronous grouting filling coefficient according to the actual working condition, and then obtain the synchronous grouting amount through theoretical calculation. In the actual grouting process, the stroke number of grouting pump is controlled according to the shield advancing speed, and the upper and lower limit of grouting pressure is set to ensure that the grout can overcome the resistance and be injected into the gap behind the tunnel lining segment wall.

[0076] However, the existing technology has the following deficiencies in the accuracy of synchronous grouting amount calculation and the adaptability of grouting pump speed control:

[0077] On the one hand, the selection of the synchronous grouting filling coefficient depends on human experience and cannot accurately reflect the geological conditions and the influence of grouting pressure. Moreover, it cannot be dynamically and automatically corrected according to the stratum settlement.

[0078] It should be noted that the prior art obtains the synchronous grout filling coefficient and the actual grouting amount of the grouting pump in a single time by measuring the single-ring excavation quality and the synchronous grouting amount of the shield, and recalculates the target synchronous grouting amount based on the synchronous grout filling coefficient value obtained in the nth ring, the actual grouting amount in a single time, and the shield excavation quality in the nth+1 ring during the construction process within the time period, and then controls and adjusts the stroke number of the grouting pump per unit time. This method solves the problem that the selection of the synchronous grouting rate depends on human experience.

[0079] However, the single-ring excavation quality measured by this method is not real due to the influence of stratum seepage water on the excavation face and the addition of soil bin improvement medium, resulting in inaccurate calculation of the synchronous grouting filling coefficient, and thus inaccurate calculation of the theoretical grouting amount.

[0080] On the other hand, the stroke number of the grouting pump is controlled according to the shield advancing speed, which involves the estimation of the stroke grouting efficiency of the grouting pump, brings errors to the calculation of the actual grouting amount, and it is difficult to quickly and accurately affect the change of the advancing speed to the grouting pump.

[0081] It should be noted that the prior art obtains the synchronous grout filling coefficient and the actual grouting amount of the grouting pump in a single time by measuring the single-ring excavation quality and the synchronous grouting amount of the shield, and recalculates the target synchronous grouting amount based on the synchronous grout filling coefficient value obtained in the nth ring, the actual grouting amount in a single time, and the shield excavation quality in the nth+1 ring during the construction process within the time period, and then controls and adjusts the stroke number of the grouting pump per unit time. This method solves the problem that the selection of the synchronous grouting rate depends on human experience.

[0082] This control method considers the influence of the change speed of the advancing speed on the control, but still has several shortcomings: first, the preset value of the advancing speed change is an artificial experience value, and whether its setting is appropriate has a great influence on the grouting control effect; second, the accuracy of the actual grouting amount calculated by the number of grouting pulses is not high; third, the traditional PID control is used, and the single parameter is difficult to adapt to the change of the advancing speed.

[0083] To solve the above problems, the inventor found in the process of researching the low efficiency of synchronous grouting control that the existing synchronous grouting filling coefficient calculation is inaccurate, the actual grouting amount calculated by the number of grouting pulses has low accuracy, and the traditional PID control cannot adapt to the change of the advancing speed. Accordingly, the inventor first uses the historical data of the tunnel formed by the same type of shield machine to build a relationship model of the synchronous grouting filling coefficient and the formation permeability coefficient, the void ratio, the average value of the grouting pressure in each partition grouting stop time period, and the formation settlement data, and identifies the model parameters by the least square method. Second, during the actual operation of the synchronous grouting of the shield machine, the data required for calculating the synchronous grouting filling coefficient model is collected and arranged, the synchronous grouting filling coefficient is calculated, and then the theoretical grouting amount is calculated. Finally, the actual grouting amount is calculated through the grout tank liquid level detection, the BP neural network adaptive incremental PID controller with feedback, and the partition grouting pressure protection, and the grouting speed is dynamically and adaptively controlled, so as to ensure that the actual grouting amount accurately tracks the theoretical grouting amount. Based on this, the embodiments of the present application provide a synchronous grouting control method, device, equipment, medium and product, which can be used in the field of shield construction, and aims to solve the problem of low efficiency of the synchronous grouting control in the prior art.

[0084] The technical solutions of the present application and how the technical solutions solve the above technical problems will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes can not be described again in some embodiments. The embodiments of the present application will be described below with reference to the drawings.

[0085] Figure 1 The system architecture schematic diagram of the synchronous grouting control method provided by the embodiments of the present application is shown in the figure, and the synchronous grouting control system is a computer device. Figure 1 In the above architecture, the above architecture includes at least one of the data acquisition device 101, the processing device 102 and the display device 103.

[0086] It can be understood that the structure shown in the embodiments of the present application does not constitute a specific limitation on the processing system architecture of the synchronous grouting control method. In other possible embodiments of the present application, the above architecture can include more or fewer components than shown in the figure, or combine certain components, or split certain components, or different component arrangement, which can be determined according to the actual application scene, and is not limited here. Figure 1 The components shown can be realized by hardware, software, or a combination of software and hardware.

[0087] In the specific implementation process, the data acquisition device 101 can include an input / output interface and can also include a communication interface. The data acquisition device 101 can be connected with the processing device through the input / output interface or the communication interface to obtain real-time data and historical data.

[0088] The processing device 102 can generate propulsion speed control commands based on the output of the adjusted proportional-integral-derivative control model.

[0089] The display device 103 can also be a touch screen or the screen of a terminal device, used to receive user commands while displaying the above-mentioned content, so as to realize interaction with the user.

[0090] It should be understood that the aforementioned processing device can be implemented by a processor reading instructions from memory and executing those instructions, or it can be implemented by a chip circuit.

[0091] Furthermore, the network architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0092] The technical solution of this application will be described in detail below with reference to specific embodiments:

[0093] Figure 2 A schematic flowchart of a synchronous grouting control method provided in this application embodiment. Figure 1 ,like Figure 2 As shown, the method includes:

[0094] S201. Collect real-time data.

[0095] S202. Preprocess the real-time data to obtain a real-time dataset.

[0096] The real-time dataset includes a first real-time data subset, a second real-time data subset, and a third real-time data subset.

[0097] For example, when the tunnel boring machine advances, the synchronous grouting system starts to operate, and the control system collects real-time data such as the tunnel boring machine's advancing speed, the rate of change of advancing speed, the grouting tank level, and ground settlement.

[0098] Furthermore, during the acquisition process, filtering and normalization are performed simultaneously to convert the acquired real-time data into dimensionless values.

[0099] The real-time data collected also includes the grouting pressure of each zone, which can be used as the output protection of the subsequent BP neural network adaptive incremental PID control module with feedback.

[0100] S203. Determine the synchronous grouting filling coefficient based on the first real-time data subset and the preset synchronous grouting filling coefficient model.

[0101] The first real-time data subset includes normalized formation permeability, porosity, partition grouting pressure set value, formation subsidence and the like.

[0102] Specifically, in a ring unit, the synchronous grouting and filling coefficient correction value of the ring is calculated through the first real-time data subset and the preset synchronous grouting and filling coefficient model, and then the synchronous grouting and filling coefficient of the ring is obtained.

[0103] Specifically, the synchronous grouting and filling coefficient calculation formula is:

[0104]

[0105] Among them, is the synchronous grouting and filling coefficient; is a bias parameter of the model, and according to the recommended value of the synchronous grouting and filling coefficient in the national standard and engineering application experience, the value in the application is a constant 1.2; is the slurry shrinkage rate; is the synchronous grouting and filling coefficient correction value.

[0106] S204, determine the theoretical grouting amount according to the second real-time data subset and the synchronous grouting and filling coefficient.

[0107] The second real-time data subset includes a first diameter of a shield machine, a second diameter of the shield machine and a shield machine advancing data set.

[0108] The first diameter of the shield machine is the outer diameter of the segment, the second diameter of the shield machine is the excavation diameter of the shield machine, and the shield machine advancing data set includes the advancing speed and the advancing time of the shield machine.

[0109] Specifically, the synchronous grouting and filling cross-sectional area is calculated according to the first diameter of the shield machine and the second diameter of the shield machine.

[0110] Specifically, the calculation formula of the synchronous grouting and filling cross-sectional area is:

[0111]

[0112] Among them, is the excavation diameter of the shield machine; is the outer diameter of the segment; is the grouting and filling cross-sectional area.

[0113] Specifically, the theoretical grouting amount is calculated according to the synchronous grouting and filling cross-sectional area, the shield machine advancing data set and the synchronous grouting and filling coefficient.

[0114] Specifically, the calculation formula of the theoretical grouting amount is:

[0115]

[0116] wherein, is a shield machine pushing speed; is a pushing time; is a theoretical grouting amount.

[0117] S205, determining an actual grouting amount according to a third real-time data subset.

[0118] wherein, the third real-time data subset includes laser ranging historical data, laser ranging original data and a tank data set.

[0119] Specifically, the laser ranging historical data includes a previous sampling period height of the slurry tank; the laser ranging original data includes a current sampling period height of the slurry tank; and the tank data set includes a bottom area of the slurry tank.

[0120] wherein, the laser ranging original data includes first original data and second original data, and the first original data and the second original data are collected by a first sensor and a second sensor respectively.

[0121] Specifically, the first original data and the second original data are respectively filtered by a median filtering algorithm to obtain first data and second data.

[0122] Specifically, whether the first data and the second data are disturbed during collection is determined by an abnormality detection strategy.

[0123] Specifically, if disturbed, the laser ranging original data is re-collected according to the abnormality detection strategy.

[0124] Specifically, if not disturbed, the actual grouting amount is calculated according to the tank data set, the laser ranging historical data, the first data and the second data.

[0125] For example, in order to more directly and accurately calculate the actual grouting amount, a laser range finder is vertically installed on the upper part of the grouting tank, and a median filtering algorithm is used to filter out interference and enhance measurement accuracy. In order to solve the interference caused by accidental damage of the sensor to the controller, two laser range finders are selected for mutual calibration.

[0126] Specifically, the calculation formula of the actual grouting amount is:

[0127]

[0128] wherein, is a previous sampling period height of the slurry tank, is a current sampling period height of the slurry tank, is a bottom area of the slurry tank, is an actual grouting amount.

[0129] S206, according to the real-time data set, the theoretical grouting amount and the actual grouting amount, the original proportional-integral-derivative control model is adjusted through the error back propagation neural network model to obtain an adjusted proportional-integral-derivative control model.

[0130] S207, the theoretical grouting amount and the actual grouting amount are input into the adjusted proportional-integral-derivative control model to generate a propelling speed control instruction through an output result of the adjusted proportional-integral-derivative control model.

[0131] In a possible embodiment, Figure 3 A shield machine synchronous grouting control system structure schematic diagram provided by the embodiment of the application is shown in the figure, Figure 3 The shield machine synchronous grouting control system includes a synchronous grouting filling coefficient model construction and identification module, a data acquisition and processing module, a synchronous grouting filling coefficient calculation module, a theoretical grouting amount calculation module and a BP neural network adaptive PID control module with feedback.

[0132] Specifically, the operation flow of the shield machine synchronous grouting control system is as follows:

[0133] First, the data acquisition and processing module acquires shield machine construction parameters and grout state data in real time, which are transmitted to the synchronous grouting filling coefficient calculation module after preprocessing, and the filling coefficient is dynamically calculated in combination with geological parameters and shield tunneling speed.

[0134] Second, the coefficient input model construction and identification module generates an adaptive filling coefficient prediction model and stores it by training historical data; the theoretical grouting amount calculation module calls the model and calculates the theoretical grouting amount in combination with parameters such as shield tail gap and soil porosity.

[0135] Third, the BP neural network adaptive PID control module with feedback performs error analysis on the theoretical value and the actual grouting amount fed back by the synchronous grouting system in real time, and dynamically adjusts the PID parameters through the neural network.

[0136] It should be noted that the system realizes adaptive adjustment of grouting parameters through deep integration of BP neural network and PID control, overcomes the defect of insufficient adaptability of traditional PID control to complex geological conditions, improves grouting amount control precision; the filling coefficient model construction and identification module continuously optimizes the prediction model through machine learning, so that the theoretical grouting amount calculation is more suitable for actual working conditions, and grout waste is reduced; the whole-process closed-loop control system dynamically corrects control deviation through a real-time feedback mechanism, effectively avoids construction risks such as segment floating and ground settlement caused by grouting lag or advance during shield machine tunneling, and significantly improves tunnel structure stability and construction safety.

[0137] The embodiment provides a synchronous grouting control method, which comprises the following steps: collecting real-time data; pre-processing the real-time data to obtain a real-time data set; determining a synchronous grouting filling coefficient according to a first real-time data subset and a preset synchronous grouting filling coefficient model; determining a theoretical grouting amount according to a second real-time data subset and the synchronous grouting filling coefficient; determining an actual grouting amount according to a third real-time data subset; adjusting an original proportional-integral-derivative control model through an error back propagation neural network model according to the real-time data set, the theoretical grouting amount and the actual grouting amount, so as to obtain an adjusted proportional-integral-derivative control model; and inputting the theoretical grouting amount and the actual grouting amount into the adjusted proportional-integral-derivative control model, so as to generate a propelling speed control instruction through an output result of the adjusted proportional-integral-derivative control model. Compared with the prior art, the synchronous grouting control efficiency is low in the accuracy of synchronous grouting amount calculation and the adaptability of grouting pump speed control. The synchronous grouting filling coefficient mathematical model is established by using the historical data of the shield tunnel, the internal relationship between the synchronous grouting filling coefficient, the influencing factors and the ground settlement data is mined, the synchronous grouting filling coefficient calculation is more accurate, the BP neural network adaptive PID control algorithm with feedback is adopted, the PID control parameters can be dynamically adjusted according to the change of the propelling speed, the adaptability of the grouting speed control is improved, the actual grouting amount calculated by using the laser range finder to monitor the liquid level of the grout tank is more accurate, and therefore the synchronous grouting control efficiency is improved.

[0138] Figure 4 A synchronous grouting control method flowchart provided by the embodiment of the application Figure 2 As shown in Figure 4 , the method further comprises the following steps before the step S202:

[0139] S401, acquire historical data, generate a plurality of data samples in units of rings, and obtain a data sample set.

[0140] For example, considering that the different grouting amounts of different excavation diameters of machine types will interfere with model construction and identification, the historical data of the same machine type shield tunnel is selected as the original identification data.

[0141] Further, for the historical data, a data sample is generated for each ring with the ring number as the statistical data interval, and each data sample comprises stratum permeability coefficient, porosity ratio, average grouting pressure of each partition grouting stop time period, stratum settlement and synchronous grouting filling coefficient.

[0142] It should be noted that a more accurate synchronous grouting filling coefficient is needed to calculate the theoretical grouting volume more precisely. Considering that the synchronous grouting filling coefficient is determined comprehensively by geological conditions, construction status, and environmental requirements, and that the historical data of the tunnel boring machine in the formed tunnel contains the intrinsic relationship between the synchronous grouting filling coefficient and its influencing factors and ground settlement, this historical data was selected as the original data for identification.

[0143] S402. Normalize the data sample set to transform it into a dimensionless value set.

[0144] In this embodiment, in order to ensure that the data samples are at the same order of magnitude, a data sample set is obtained by collecting data samples, and the data sample set is normalized to convert it into dimensionless values, thus obtaining a set of dimensionless values.

[0145] S403. Construct a synchronous grouting filling coefficient model based on the dimensionless value set.

[0146] Specifically, the formula for the synchronous grouting filling coefficient model is as follows:

[0147]

[0148] in, This refers to the synchronous grouting filling coefficient; The bias parameter of the model is set to a constant of 1.2 in this invention, based on the national standard's recommended value for the synchronous grouting filling coefficient and engineering application experience. The formation permeability coefficient, These are the model parameters for the formation permeability coefficient; Porosity These are the model parameters for the porosity. This represents the average grouting pressure during the grouting stop time period in the first zone. For the first The average grouting pressure during the grouting stop time period in each zone. The model parameters represent the average grouting pressure during the grouting stop time period in the first zone. For the first Model parameters for the average grouting pressure during the grouting stop time period in the zone. For transpose, The number of zones for synchronous grouting of the tunnel boring machine; This is due to ground subsidence. These are the model parameters for ground subsidence; This represents the slurry shrinkage rate.

[0149] It should be noted that, considering the grout used in the same tunnel section Since the coefficient is generally a fixed constant, the formula for the synchronous grouting filling coefficient model is updated as follows:

[0150]

[0151] wherein, is a synchronous grouting filling coefficient correction value.

[0152] S404, according to the dimensionless value set and the least square method, a synchronous grouting filling coefficient model is solved to obtain a model parameter solution set.

[0153] wherein, the model parameter solution set includes multiple model parameter solutions, and each model parameter solution corresponds to an influence parameter.

[0154] S405, according to the model parameter solution and a preset error threshold, the reliability of the model parameter solution is judged.

[0155] S406, if a model parameter solution in the model parameter solution set is not reliable, a preset adjustment strategy is adjusted.

[0156] S407, if all model parameter solutions in the model parameter solution set are reliable, the synchronous grouting filling coefficient model is saved.

[0157] For example, because the synchronous grouting filling coefficient model in the updating formula is a linear model, the least square method can be used to solve the model parameter.

[0158] Firstly, the following vector is defined:

[0159]

[0160]

[0161] wherein, is a model parameter vector; is the i-th identification data vector; is the i-th identification data vector; is the formation permeability value in the i-th identification data vector; is the porosity value in the i-th identification data vector; is the average grouting pressure value of the first partition grouting stop time period in the i-th identification data vector, is the average grouting pressure value of the j-th partition grouting stop time period in the i-th identification data vector, is the number of partitions of the synchronous grouting of the shield machine; is the formation settlement value in the i-th identification data vector, is the transposition.

[0162] ​​​​​​Secondly, based on the vector defined above and The update formula can be rewritten in matrix form:

[0163]

[0164] Secondly, the current number of identification data samples is Organize the data samples into a matrix form:

[0165]

[0166] in, This is a vector of correction values ​​for the synchronous grouting filling coefficient. This is the correction value for the synchronous grouting filling coefficient in the first identified data. This is the correction value for the synchronous grouting filling coefficient in the second identification data. For the first Correction value for synchronous grouting filling coefficient in individual identification data; To identify the data vector matrix, The first identification data vector, This is the second identification data vector. For the first A single identification data vector.

[0167] Finally, based on the least squares method, the parameter solution of the model is:

[0168]

[0169] In one possible embodiment, Figure 5 This is a schematic diagram of the shield machine synchronous grouting filling coefficient model construction and identification module provided in the embodiments of this application, as shown below. Figure 5 As shown, this module cleans, normalizes, and extracts features from historical construction data of tunnels formed by the same type of shield tunneling machine through the preprocessing module to form a standardized dataset; then it enters the model building stage, and establishes a nonlinear mathematical model based on the preprocessed data, which includes the synchronous grouting filling coefficient, geological parameters, tunneling speed, grout characteristics, and other multi-dimensional variables; finally, the model is iteratively optimized through the parameter identification module to determine the optimal coefficient combination and save it as a callable model.

[0170] It should be noted that through deep mining of historical construction data, the filling coefficient mathematical model constructed can accurately reflect the dynamic correlation between geological conditions and grouting parameters, improve the grouting quantity prediction accuracy compared with the traditional empirical formula method, and effectively reduce the waste of slurry; the model parameter identification process adopts machine learning algorithm for automatic optimization, avoiding subjective error of manual parameter adjustment, and ensuring the robustness of the model under different geological conditions; the model saving function supports cross-project reuse, shortens the new project start-up cycle, and reduces the repeated modeling cost.

[0171] In the embodiment, by establishing a synchronous grouting filling coefficient mathematical model, the internal relationship between the synchronous grouting filling coefficient and its influencing factors and ground subsidence data is mined, the model parameters are identified by using a large amount of formed tunnel historical data, the synchronous grouting filling coefficient calculation is more accurate and reliable, and therefore the synchronous grouting control efficiency is improved.

[0172] Figure 6 A synchronous grouting control method flowchart provided by the embodiment of the present application Figure 3 As shown in Figure 6 , the specific implementation steps of S206 include:

[0173] S601, obtaining input layer output values and feedback layer output values according to the real-time data set, the theoretical grouting quantity, the actual grouting quantity and the weight parameter set.

[0174] S602, adding the input layer output values and the feedback layer output values to obtain hidden layer input values.

[0175] S603, obtaining an output layer output value set according to the hidden layer input values and the weight parameter set.

[0176] S604, adjusting the original proportional-integral-derivative control model according to the output layer output value set to obtain an adjusted proportional-integral-derivative control model.

[0177] For example, the present application adopts an incremental proportional-integral-derivative control model:

[0178]

[0179] Among them, , , are the proportional, integral and differential coefficients of the incremental PID controller at the kth moment, is the grouting quantity deviation at the kth moment, is the grouting quantity deviation at the kth moment, is the grouting quantity deviation at the kth moment, is the grouting quantity deviation at the kth moment, is the grouting quantity deviation at the kth moment, is the grouting quantity deviation at the kth moment, is the grouting quantity deviation at the kth moment, The grouting pump speed control output instruction of the time controller, The grouting pump speed control output instruction of the time controller, The grouting pump speed control output instruction of the time controller, The grouting pump speed control output instruction of the time controller,

[0180] Specifically, the formula is based on grouting quantity deviation Dynamic adjustment of grouting pump speed increment .

[0181] Further, in the theoretical grouting quantity tracking process, the grouting speed control needs to dynamically adapt to the change of the propulsion speed, and a single PID control parameter is difficult to have a good control effect, and a PID control parameter that can react to the change of the propulsion speed in real time needs to be designed. The BP neural network has good nonlinear description capability, and the propulsion speed and its change can be introduced into the input of the neural network, but the traditional BP neural network has no feedback, and the time sequence correlation characteristics of the propulsion speed and its change cannot be reflected on the output of the neural network. Therefore, in order to mine the time sequence correlation characteristics of the propulsion speed and its change, a feedback layer is added to the traditional BP neural network, and the output of the feedback layer is added to the output of the input layer as the input of the hidden layer, and the calculation process is as follows:

[0182]

[0183] Wherein, Indicates the time ; The input vector of the input layer at the time , The propulsion speed at the time The change rate of the propulsion speed at the time The grouting quantity deviation at the time The grouting quantity deviation change rate at the time The input of the hidden layer at the time The weight of the hidden layer at the time The node of the feedback layer at the time The weight of the feedback layer at the time The number of input layer nodes is 5, The number of feedback layer nodes, The number of hidden layer nodes, i, f, h are node codes; The output of the hidden layer at the time The activation function; This is the input to the l-th node at time k in the output layer. The weights from the l-th node at time k in the output layer to the h-th node in the hidden layer are given. This is the output of the l-th node at time k in the output layer; The first output of the output layer at time k is... ; This is the second output of the output layer at time k, which is... ; This is the third output of the output layer at time k, which is... ; Activation function The specific form of expression, Activation function Specific forms of expression.

[0184] Specifically, the hidden layer input integrates the current input (propulsion speed, deviation, etc.) and the feedback layer output to enhance timing characteristics. This enables the output layer to dynamically generate PID parameters.

[0185] Optionally, the weight parameter set can be automatically updated and adjusted using the cost function.

[0186] Specifically, the cost function is:

[0187]

[0188] Optionally, the weight parameter set can also be modified using gradient descent.

[0189] Specifically, the process of correcting the weight parameters according to the gradient descent method is as follows:

[0190]

[0191] in, The inertia coefficient, For learning rate, For the first The increment of the weights from the l-th node in the output layer to the h-th node in the hidden layer at time step [time]. Let sgn be the increment of the weights from the l-th node in the output layer to the h-th node in the hidden layer at time k, and let sgn be the sign function. Let be the increase in weight from the h-th node in the hidden layer to the i-th node in the input layer at time k. For the first The increase in weight from the h-th node in the hidden layer to the i-th node in the input layer at time step 1. For the feedback layer at time k, The node is connected to the hidden layer. The increase in the weight of each node. For the first the increase value of the weight of the fth node of the feedback layer to the hth node of the hidden layer.

[0192] In a possible embodiment, Figure 7 A BP neural network adaptive incremental PID grouting speed control structure with feedback provided by the embodiment of the application is shown in FIG. 1. Figure 7 As shown in the figure, the structure includes five parts, namely, an incremental PID controller, a BP neural network with feedback, a partition grouting pressure protection module, a grouting tank liquid level detection module, and an actual grouting calculation module.

[0193] Specifically, the propulsion speed and the rate of change are input into the BP neural network as dynamic sensing signals, and the PID control parameters are output after the operation of the hidden layer weight matrix; the incremental PID controller calculates the deviation by combining the theoretical grouting expectation value and the actual grouting amount, and dynamically adjusts the control amount through the proportional, integral, and differential three links; the partition grouting pressure protection module performs safety threshold checking on the adjusted control signal to ensure that the working pressure of each partition grouting pump is within a safe range and prevent overpressure or underpressure; the grouting tank liquid level detection module monitors the slurry reserve (liquid level change) in real time to ensure continuous operation; and finally, the partition grouting pressure is fed back to the neural network feedback layer as the core feedback signal, and the network weight is dynamically corrected through the error back propagation algorithm.

[0194] The partition grouting pressure protection module sets a maximum pressure limit value for each partition to prevent pipe explosion or excessive pressure disturbance to the stratum, and sets the grouting pump speed control output to 0 when the grouting pressure is greater than the maximum pressure limit value.

[0195] It should be noted that when the shield machine is tunneling, the data acquisition and processing module, the synchronous grouting filling coefficient calculation module, the theoretical grouting amount calculation module, and the BP neural network adaptive incremental PID control module with feedback form a grouting speed closed-loop control, and the partition grouting pressure protection module is introduced into the closed-loop control to control accurately and safely.

[0196] In the embodiment, the propulsion speed, the rate of change of the propulsion speed, the grouting amount deviation, and the rate of change of the grouting amount deviation are collected as the input of the BP neural network, the nonlinear expression capability of the BP neural network is fully utilized, a feedback layer is designed to feed back the output of the BP hidden layer to the input of the hidden layer, the time series correlation characteristics of the propulsion speed and its change are fully tapped, and thus the PID control parameters can be dynamically adjusted according to the change of the propulsion speed, the adaptability of the grouting speed control is improved, the anti-interference ability of the system is improved, and the grouting control precision is also improved. Therefore, the synchronous grouting control efficiency is improved.

[0197] Figure 8 A structure schematic diagram of a synchronous grouting control device provided by the embodiment of the application is shown in FIG. 1.Figure 8 As shown in the figure, the device comprises: a collection module 81, a preprocessing module 82, a first determination module 83, a second determination module 84, a third determination module 85, an adjustment module 86, and a generation module 87.

[0198] The collection module 81 is configured to collect real-time data.

[0199] The preprocessing module 82 is configured to preprocess the real-time data to obtain a real-time data set; wherein the real-time data set comprises a first real-time data subset, a second real-time data subset, and a third real-time data subset.

[0200] The first determination module 83 is configured to determine a synchronous grouting filling coefficient according to the first real-time data subset and a preset synchronous grouting filling coefficient model.

[0201] The second determination module 84 is configured to determine a theoretical grouting amount according to the second real-time data subset and the synchronous grouting filling coefficient.

[0202] The third determination module 85 is configured to determine an actual grouting amount according to the third real-time data subset.

[0203] The adjustment module 86 is configured to adjust an original proportional-integral-derivative control model through an error back propagation neural network model according to the real-time data set, the theoretical grouting amount, and the actual grouting amount, to obtain an adjusted proportional-integral-derivative control model.

[0204] The generation module 87 is configured to input the theoretical grouting amount and the actual grouting amount into the adjusted proportional-integral-derivative control model, to generate a propulsion speed control instruction through an output result of the adjusted proportional-integral-derivative control model.

[0205] In a possible design, before the real-time data is preprocessed to obtain the real-time data set, the device further comprises:

[0206] The preprocessing module 82 is further configured to obtain historical data, generate a plurality of data samples in a ring unit, and obtain a data sample set.

[0207] The data sample set is normalized to convert into a dimensionless value set.

[0208] The synchronous grouting filling coefficient model is constructed according to the dimensionless value set.

[0209] In a possible design, after the synchronous grouting filling coefficient model is constructed according to the dimensionless value set, the device further comprises:

[0210] The preprocessing module 82 is further configured to solve the synchronous grouting filling coefficient model according to the dimensionless value set and a least square method to obtain a model parameter solution set, wherein the model parameter solution set includes a plurality of model parameter solutions, and each model parameter solution corresponds to an influence parameter;

[0211] According to the model parameter solution and a preset error threshold, the reliability of the model parameter solution is determined;

[0212] If the model parameter solution in the model parameter solution set is not reliable, the preset adjustment strategy is adjusted;

[0213] If all the model parameter solutions in the model parameter solution set are reliable, the synchronous grouting filling coefficient model is saved.

[0214] In a possible design, the second real-time data subset includes a first diameter of the shield machine, a second diameter of the shield machine, and a shield machine propulsion data set;

[0215] The second determining module 84 is further configured to determine a theoretical grouting amount according to the second real-time data subset and the synchronous grouting filling coefficient, including:

[0216] The synchronous grouting filling cross-sectional area is calculated according to the first diameter of the shield machine and the second diameter of the shield machine;

[0217] The theoretical grouting amount is calculated according to the synchronous grouting filling cross-sectional area, the shield machine propulsion data set, and the synchronous grouting filling coefficient.

[0218] In a possible design, the third real-time data subset includes laser ranging historical data, laser ranging original data, and a tank data set;

[0219] The laser ranging original data includes first original data and second original data, and the first original data and the second original data are respectively collected by a first sensor and a second sensor independent of each other;

[0220] The actual grouting amount is determined according to the third real-time data subset, including:

[0221] The third determining module 85 is further configured to perform filtering processing on the first original data and the second original data respectively by a median filtering algorithm to obtain first data and second data;

[0222] Whether the first data and the second data are disturbed during collection is determined by an abnormality detection strategy;

[0223] If disturbed, the laser ranging original data is re-collected according to the abnormality detection strategy processing;

[0224] If not disturbed, the actual grouting amount is calculated according to the tank data set, the laser ranging historical data, the first data, and the second data.

[0225] In a possible design, the error back propagation neural network model comprises an input layer, a hidden layer, a feedback layer, and an output layer.

[0226] According to the real-time data set, the theoretical grouting amount, and the actual grouting amount, the original proportional-integral-derivative control model is adjusted by using the error back propagation neural network model to obtain an adjusted proportional-integral-derivative control model, comprising the following steps.

[0227] The adjustment module 86 is further configured to obtain the input layer output value and the feedback layer output value according to the real-time data set, the theoretical grouting amount, the actual grouting amount, and the weight parameter set.

[0228] The input layer output value and the feedback layer output value are added to obtain a hidden layer input value.

[0229] According to the hidden layer input value and the weight parameter set, an output layer output value set is obtained.

[0230] The original proportional-integral-derivative control model is adjusted according to the output layer output value set to obtain an adjusted proportional-integral-derivative control model.

[0231] In a possible design, the weight parameter set is automatically updated and adjusted by using a cost function.

[0232] The weight parameter set is further corrected by using a gradient descent method.

[0233] The synchronous grouting control device provided in this embodiment can perform the synchronous grouting control method provided in the above embodiments, and has similar implementation principles and technical effects, which will not be described here again.

[0234] In the specific implementation of the above-described synchronous grouting control method, each module can be implemented as a processor. The processor can execute computer execution instructions stored in the memory, so that the processor executes the above-described synchronous grouting control method.

[0235] Figure 9 A structural schematic diagram of a synchronous grouting control device provided in this embodiment is shown in FIG. 8. Figure 9 As shown in FIG. 8, the synchronous grouting control device 90 includes at least one processor 91 and a memory 92. The synchronous grouting control device 90 further includes a communication component 93. The processor 91, the memory 92, and the communication component 93 are connected through a second bus 94.

[0236] In the specific implementation process, the at least one processor 91 executes computer execution instructions stored in the memory 92, so that the at least one processor 91 executes a method in the field of shield construction as executed by the above-described synchronous grouting control device.

[0237] The specific implementation process of the processor 91 can refer to the method embodiments described above, which have similar implementation principles and technical effects, and thus will not be described here again.

[0238] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the disclosed method can be directly embodied as hardware processor execution, or executed by a combination of hardware and software modules in the processor.

[0239] The memory can include a high-speed RAM memory, and can also include a non-volatile storage NVM, such as at least one disk memory.

[0240] The second bus can be an industry standard architecture (ISA) bus, a peripheral component (PCI) bus, or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, the bus in the drawings of the present application does not limit to only one bus or one type of bus.

[0241] The functions realized by the synchronous grouting control device and the master control device described above are introduced for the scheme provided by the embodiments of the present application. It can be understood that the synchronous grouting control device or the master control device contains the corresponding hardware structure and / or software modules for executing each function in order to realize the above functions. The units and algorithm steps of each example described in combination with the embodiments disclosed in the embodiments of the present application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software driven hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the technical solutions of the embodiments of the present application.

[0242] The application further provides a computer readable storage medium, and the computer readable storage medium stores computer execution instructions.

[0243] The readable storage medium can be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0244] An exemplary readable storage medium is coupled to the processor, so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in the synchronous grouting control device or the master control device.

[0245] The application further provides a computer program product, which comprises a computer program stored in a readable storage medium, and at least one processor of the synchronous grouting control device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to enable the synchronous grouting control device to execute the scheme provided in any one of the above embodiments.

[0246] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware. The foregoing program can be stored in a computer readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the foregoing storage medium includes ROM, RAM, magnetic disk or optical disk and various storage media that can store program codes.

[0247] So far, the technical solutions of the present application have been described in combination with the preferred embodiments shown in the drawings, but those skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments, and the above examples are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for controlling synchronous grouting, characterized in that, include: Collect real-time data; The real-time data is preprocessed to obtain a real-time dataset; wherein the real-time dataset includes a first real-time data subset, a second real-time data subset, and a third real-time data subset; Based on the first real-time data subset and the preset synchronous grouting and filling coefficient model, the synchronous grouting and filling coefficient is determined. The theoretical grouting volume is determined based on the second real-time data subset and the synchronous grouting filling coefficient; The actual grouting volume is determined based on the third real-time data subset. Based on the real-time dataset, the theoretical grouting volume, and the actual grouting volume, the original proportional-integral-derivative control model is adjusted using an error backpropagation neural network model to obtain the adjusted proportional-integral-derivative control model. The theoretical grouting volume and the actual grouting volume are input into the adjusted proportional-integral-derivative control model, so as to generate propulsion speed control commands based on the output of the adjusted proportional-integral-derivative control model.

2. The method according to claim 1, characterized in that, Before preprocessing the real-time data to obtain the real-time dataset, the method further includes: Acquire historical data and generate multiple data samples in ring units to obtain a data sample set; The data sample set is normalized and transformed into a dimensionless value set; The synchronous grouting filling coefficient model is constructed based on the dimensionless value set.

3. The method according to claim 2, characterized in that, After constructing the synchronous grouting filling coefficient model based on the dimensionless value set, the method further includes: The synchronous grouting filling coefficient model is solved by using the dimensionless value set and the least squares method to obtain the model parameter solution set, wherein the model parameter solution set includes multiple model parameter solutions, and each model parameter solution corresponds to an influence parameter; The reliability of the model parameter solution is determined based on the model parameter solution and the preset error threshold. If any of the model parameter solutions in the solution set are unreliable, then adjustments are made according to a preset adjustment strategy; If all model parameter solutions in the model parameter solution set are reliable, then the synchronous grouting filling coefficient model is saved.

4. The method according to claim 3, characterized in that, The second real-time data subset includes the first diameter of the tunnel boring machine, the second diameter of the tunnel boring machine, and the tunnel boring machine propulsion dataset; The step of determining the theoretical grouting volume based on the second real-time data subset and the synchronous grouting filling coefficient includes: The synchronous grouting and filling cross-sectional area is calculated based on the first diameter and the second diameter of the tunnel boring machine; The theoretical grouting volume is calculated based on the synchronous grouting filling cross-sectional area, the tunnel boring machine propulsion data set, and the synchronous grouting filling coefficient.

5. The method according to claim 4, characterized in that, The third real-time data subset includes historical laser ranging data, raw laser ranging data, and tank dataset. The laser ranging raw data includes first raw data and second raw data, which are respectively collected from a first sensor and a second sensor that are independent of each other. Determining the actual grouting volume based on the third real-time data subset includes: The first original data and the second original data are filtered out by the median filtering algorithm to obtain the first data and the second data. An anomaly detection strategy is used to determine whether the first and second data were interfered with during acquisition. If interference occurs, the anomaly detection strategy will be followed to re-acquire the original laser ranging data; If there is no interference, the actual grouting volume is calculated based on the tank dataset, the historical laser ranging data, the first data, and the second data.

6. The method according to claim 5, characterized in that, The backpropagation neural network model includes an input layer, a hidden layer, a feedback layer, and an output layer. The step of adjusting the original proportional-integral-derivative (PI-DE) control model using an error backpropagation neural network model based on the real-time dataset, the theoretical grouting volume, and the actual grouting volume to obtain the adjusted PI-DE control model includes: Based on the real-time dataset, the theoretical grouting volume, the actual grouting volume, and the weight parameter set, the input layer output value and the feedback layer output value are obtained. The input layer output value is added to the feedback layer output value to obtain the hidden layer input value; Based on the hidden layer input values ​​and the weight parameter set, the output layer output value set is obtained; The original proportional-integral-derivative control model is adjusted according to the set of output values ​​of the output layer to obtain the adjusted proportional-integral-derivative control model.

7. The method according to any one of claims 1 to 6, characterized in that, The set of weight parameters is automatically updated and adjusted through a cost function; The set of weight parameters is also corrected using gradient descent.

8. A synchronous grouting control device, characterized in that, include: The data acquisition module is used to collect real-time data. A preprocessing module is used to preprocess the real-time data to obtain a real-time dataset; wherein the real-time dataset includes a first real-time data subset, a second real-time data subset, and a third real-time data subset; The first determining module is used to determine the synchronous grouting filling coefficient based on the first real-time data subset and the preset synchronous grouting filling coefficient model. The second determining module is used to determine the theoretical grouting volume based on the second real-time data subset and the synchronous grouting filling coefficient; The third determining module is used to determine the actual grouting volume based on the third real-time data subset. The adjustment module is used to adjust the original proportional-integral-derivative control model based on the real-time dataset, the theoretical grouting volume, and the actual grouting volume through an error backpropagation neural network model, so as to obtain the adjusted proportional-integral-derivative control model. The generation module is used to input the theoretical grouting volume and the actual grouting volume into the adjusted proportional-integral-derivative control model, so as to generate propulsion speed control commands based on the output results of the adjusted proportional-integral-derivative control model.

9. A synchronous grouting control device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

11. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images