Blind area cleaning method, device and equipment based on soil bin partition stress and medium

Abstract

The application relates to the field of pipe jacking construction technology, and discloses a blind area cleaning method, device, equipment and medium based on soil bin partition stress, which comprises the following steps: generating the load distribution borne by the front surface of the soil bin partition through a trained machine learning model; obtaining the pressure of the blind area and the pressure of the non-blind area in the region where the soil bin partition is located according to the load distribution; comparing the pressure of the blind area with the pressure of the non-blind area to generate the ratio between the pressure of the blind area and the pressure of the non-blind area; comparing the ratio with a set value to obtain the comparison result of the ratio and the set value; when the comparison result is that the ratio is greater than a starting threshold value and less than a first proportion of the set value, a first cleaning decision is executed; when the ratio is not less than a first proportion of the set value and not greater than a second proportion of the set value, a second cleaning decision is executed; and when the ratio is greater than a second proportion of the set value, a third cleaning decision is executed. The application can improve the cleaning efficiency of the excavation blind area in the rectangular pipe jacking machine tunneling process.

Description

Technical Field

[0001] This application relates to the field of pipe jacking construction technology, and in particular to a method, apparatus, equipment and medium for blind spot cleaning based on soil chamber diaphragm stress. Background Technology

[0002] In underground tunneling operations, rectangular pipe jacking machines can significantly improve the cutting rate of the excavation face due to their unique multi-cutterhead design. However, due to the inherent characteristics of the cutterhead structure and movement trajectory, there are cutting blind spots in the shield area of ​​the rectangular pipe jacking machine where the cutting trajectories of multiple cutterheads do not cover the area.

[0003] During long-distance jacking, the cutterhead structure and circular cutting trajectory of rectangular pipe jacking machines inevitably create blind zones. Soil in these blind zones is difficult to cut effectively and tends to accumulate into large clumps that cannot be discharged through the soil chamber. This increases the jacking resistance of the rectangular pipe jacking machine, making it difficult for it to move in the intended direction and causing it to easily deviate to the left, right, or up and down. Once the rectangular pipe jacking machine deviates, the subsequently laid tunnel will also deviate from the originally planned axis position, causing tunnel axis deviation. This deviation not only makes the overall tunnel structure fail to meet design requirements, affecting the tunnel's functionality and stability, but also brings great difficulties to subsequent tunnel interior decoration, equipment installation, and other processes. Therefore, how to clear these blind zones is a technical problem that urgently needs to be solved. Summary of the Invention

[0004] This application provides a method, apparatus, equipment, and medium for blind spot cleaning based on the stress of earthwork diaphragms, in order to solve the aforementioned technical problem of how to perform blind spot cleaning.

[0005] In a first aspect, embodiments of this application provide a blind spot cleaning method based on the stress of a soil silo partition, applied to an electronic device. The electronic device is connected to a distributed optical fiber sensing system, and the sensing optical fibers of the distributed optical fiber sensing system are deployed on the rear surface of the soil silo partition of a rectangular pipe jacking machine. The blind spot cleaning method includes:

[0006] Send a data acquisition request to the distributed fiber optic sensing system and receive the current stress data returned by the distributed fiber optic sensing system based on the data acquisition request;

[0007] Input the current stress data into the visualization tool, and generate a stress distribution map of the soil chamber diaphragm using the visualization tool;

[0008] The stress distribution map of the earth chamber partition is input into the trained machine learning model, and the load distribution on the front surface of the earth chamber partition is generated by the trained machine learning model.

[0009] Based on the load distribution on the front surface of the earthwork partition, the pressure in the blind zone and the pressure in the non-blind zone of the area where the earthwork partition is located are obtained. The pressure in the blind zone is compared with the pressure in the non-blind zone to generate the ratio between the pressure in the blind zone and the pressure in the non-blind zone.

[0010] When the ratio between the pressure in the blind zone and the pressure in the non-blind zone is greater than the activation threshold, the ratio is compared with a set value to obtain the comparison result. If the comparison result is that the ratio is greater than the activation threshold and less than the first proportion of the set value, a first cleaning decision is executed. If the ratio is not less than the first proportion of the set value and not greater than the second proportion of the set value, a second cleaning decision is executed. If the ratio is greater than the second proportion of the set value, a third cleaning decision is executed. The first cleaning decision is to activate only the outer nozzle of the dual-row nozzle to create eddies, which are used to flush the soil in the blind zone. The second cleaning decision is to activate the dual-row nozzle and control the outer and inner nozzles of the dual-row nozzle to spray conical water curtains within the medium-low pressure range. The third cleaning decision is to activate the dual-row nozzle and control the outer nozzle of the dual-row nozzle to spray conical water curtains within the medium-low pressure range, and control the inner nozzle of the dual-row nozzle to spray conical water curtains within the high pressure range. The conical water curtains within the medium-low pressure range are used to wash the soil in the blind zone, and the conical water curtains within the high pressure range are used to break up the soil in the blind zone.

[0011] In one possible implementation of the first aspect, when the comparison result is a first proportion that is greater than a start threshold and less than a set value, a first cleanup decision is executed, including:

[0012] When the comparison result is a ratio greater than the start threshold and less than the set value, the load distribution on the front surface of the soil chamber partition, the feature extraction information of the blind zone, and the number of nozzles are used as the query conditions for the current case. The query conditions for the current case are converted into the feature vector of the current case. The feature vector of the current case is submitted to the query engine of the vector database. The query engine performs a similarity search on the feature vector of the current case and generates search results. In the search results, the similarity between each historical case and the current case in the vector database is obtained. The case with the highest similarity is selected as the target case. The vector database stores the feature vector of each historical case. The feature extraction information of the blind zone includes the load distribution of the blind zone and the geometric feature vector of the blind zone.

[0013] Extract the preset water pressure, preset water volume, and preset deflection angle from the historical cleaning parameters stored in the target case. Select the preset water pressure, preset water volume, and preset deflection angle as the current water pressure, current water volume, and current deflection angle for the first cleaning decision. Encapsulate the current water pressure, current water volume, and current deflection angle of the first cleaning decision into a vortex creation instruction and send the vortex creation instruction to the execution mechanism.

[0014] In one possible implementation of the first aspect, preset water pressure, preset water volume, and preset deflection angle are extracted from historical cleaning parameters stored in the target case. These preset water pressure, water volume, and deflection angle are selected as the current water pressure, water volume, and deflection angle for the first cleaning decision. The current water pressure, water volume, and deflection angle of the first cleaning decision are encapsulated into eddy current creation instructions, and these instructions are sent to the execution mechanism, including:

[0015] Extract preset water pressure, preset water volume, and preset deflection angle from the historical cleanup parameters stored in the target case. Input the preset water pressure, preset water volume, and preset deflection angle into the simulation tool. The simulation tool generates the water flow velocity in the internal region of the vortex. The simulation tool is a numerical simulation tool based on the principle of fluid dynamics.

[0016] Based on the water flow velocity in the internal region of the vortex and the preset influence model, the influence radius of the vortex is generated. Based on the influence radius of the vortex, the influence area of ​​the vortex is generated. When the influence area of ​​the vortex is greater than the area in the feature extraction information of the blind zone, preset water pressure, preset water volume, and preset deflection angle are selected as the current water pressure, current water volume, and current deflection angle of the first cleaning decision. The current water pressure, current water volume, and current deflection angle of the first cleaning decision are encapsulated into the vortex creation instruction and sent to the execution mechanism.

[0017] In one possible implementation of the first aspect, the influence model is defined as follows:

[0018] ;

[0019] ;

[0020] Indicates the radius of influence of the eddy current; Represents a constant; Indicates the radius of the nozzle;

[0021] This indicates the pressure difference between the nozzle outlet and the vortex. The greater the pressure difference between the nozzle outlet and the vortex, the stronger the rotational energy of the vortex; the smaller the pressure difference between the nozzle outlet and the vortex, the weaker the rotational energy of the vortex.

[0022] This indicates the average flow velocity at the nozzle exit. This represents the velocity difference between the average flow velocity at the nozzle outlet and the water flow velocity within the vortex's interior region.

[0023] In one possible implementation of the first aspect, after executing a blind spot clearing decision when the ratio between the pressure in the blind spot and the pressure in the non-blind spot is greater than a trigger threshold, the blind spot clearing method includes:

[0024] Acquire the working data of the rectangular pipe jacking machine, read the preset storage time, and determine whether the current time is the storage time; if the current time is the storage time, connect to the vector database and store the working data and current stress data in the vector database.

[0025] In one possible implementation of the first aspect, before sending a data acquisition request to the distributed optical fiber sensing system and receiving current stress data returned by the distributed optical fiber sensing system according to the data acquisition request, the blind spot clearing method includes:

[0026] Obtain preset stress data and preset stress distribution map of the partition plate. Combine the preset stress data and preset stress distribution map of the partition plate into training samples. Combine different training samples into a training set. Use the training set to train the machine learning model to obtain the trained machine learning model.

[0027] In one possible implementation of the first aspect, the first ratio and the second ratio are 50% and 75%, respectively.

[0028] Alternatively, the first and second proportions are 60% and 85% respectively;

[0029] Alternatively, the first and second proportions are 55% and 65% respectively.

[0030] Secondly, embodiments of this application provide a blind spot cleaning device based on soil chamber baffle stress, applied to an electronic device. The electronic device is connected to a distributed optical fiber sensing system, and the sensing optical fibers of the distributed optical fiber sensing system are arranged on the rear surface of the soil chamber baffle of the rectangular pipe jacking machine, including:

[0031] The receiving module is used to send a data acquisition request to the distributed fiber optic sensing system and receive the current stress data returned by the distributed fiber optic sensing system based on the data acquisition request.

[0032] The first input module is used to input the current stress data into the visualization tool, and the visualization tool generates a stress distribution map of the soil chamber diaphragm.

[0033] The second input module is used to input the stress distribution map of the soil chamber partition into the trained machine learning model, and generate the load distribution on the front surface of the soil chamber partition through the trained machine learning model.

[0034] The generation module is used to obtain the pressure in the blind zone and the pressure in the non-blind zone of the area where the soil silo is located based on the load distribution on the front surface of the soil silo. The pressure in the blind zone is compared with the pressure in the non-blind zone to generate the ratio between the pressure in the blind zone and the pressure in the non-blind zone.

[0035] The cleaning module is used to compare the ratio between the pressure in the blind zone and the pressure in the non-blind zone when the ratio is greater than the activation threshold, and obtain the comparison result. When the comparison result is that the ratio is greater than the activation threshold and less than the first proportion of the set value, a first cleaning decision is executed. When the ratio is not less than the first proportion of the set value and not greater than the second proportion of the set value, a second cleaning decision is executed. When the ratio is greater than the second proportion of the set value, a third cleaning decision is executed. The first cleaning decision is to only activate the outer nozzle of the dual-row nozzle to create eddies, which are used to flush the soil in the blind zone. The second cleaning decision is to activate the dual-row nozzle and control the outer and inner nozzles of the dual-row nozzle to spray conical water curtains in the medium-low pressure range. The third cleaning decision is to activate the dual-row nozzle and control the outer nozzle of the dual-row nozzle to spray conical water curtains in the medium-low pressure range, and control the inner nozzle of the dual-row nozzle to spray conical water curtains in the high pressure range. The conical water curtains in the medium-low pressure range are used to wash the soil in the blind zone, and the conical water curtains in the high pressure range are used to break up the soil in the blind zone.

[0036] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the blind spot clearing method described in the first aspect above.

[0037] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the blind spot clearing method described in the first aspect.

[0038] Fifthly, embodiments of this application provide a computer program product that, when run on an electronic device, causes the electronic device to execute the blind spot clearing method described in the first aspect.

[0039] The beneficial effects of the embodiments of this application are as follows:

[0040] Firstly, when the ratio between the pressure in the blind zone and the pressure in the non-blind zone is greater than the activation threshold, the ratio is compared with a set value to obtain the comparison result. When the comparison result is that the ratio is greater than the activation threshold and less than the first proportion of the set value, a first cleaning decision is executed. When the ratio is not less than the first proportion of the set value and not greater than the second proportion of the set value, a second cleaning decision is executed. When the ratio is greater than the second proportion of the set value, a third cleaning decision is executed. Since the first, second, and third cleaning decisions are executed automatically without manual operation, the cleaning time of the blind zone is reduced, which is conducive to improving the cleaning efficiency of the blind zone.

[0041] Secondly, since the first cleaning decision only uses the outer nozzle of the double-row nozzle to create eddies, and the soil in the blind area is washed by the eddies, the first cleaning decision can clean the blind area in a gentler way, thereby reducing the disturbance to the strata. This is of great significance for protecting the ecological environment and reducing the impact of construction on the surrounding environment. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is an application scenario diagram of the blind spot clearing method provided in the embodiments of this application;

[0044] Figure 2 This is a flowchart illustrating the blind spot clearing method provided in the embodiments of this application;

[0045] Figure 3 A flowchart illustrating the storage of working data provided in this application embodiment;

[0046] Figure 4 A schematic block diagram of the blind spot clearing device provided in the embodiments of this application;

[0047] Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application;

[0048] Figure 6 This is an application flowchart of the blind spot clearing method provided in the embodiments of this application;

[0049] Figure 7 This is a plan view of the rectangular pipe jacking machine used in the embodiments of this application;

[0050] Figure 8 A diagram of the optical fiber distribution network provided in the embodiments of this application. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0052] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0053] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0054] The blind spot clearing method provided in this application embodiment can be applied to electronic devices. The electronic devices are connected to a distributed optical fiber sensing system. The sensing optical fiber of the distributed optical fiber sensing system is laid on the rear surface of the soil chamber partition of the rectangular pipe jacking machine. The electronic devices include, but are not limited to, servers, mobile phones, tablets, wearable devices, vehicle-mounted devices, and laptops. This application embodiment does not impose any restrictions on the specific type of electronic devices.

[0055] Please see Figure 1 , Figure 1 The application scenario diagram of the blind spot clearing method provided in the embodiments of this application is described in detail below:

[0056] The electronic device connects to the distributed fiber optic sensing system, sends a data acquisition request to the distributed fiber optic sensing system, and receives the current stress data returned by the distributed fiber optic sensing system based on the data acquisition request.

[0057] The sensing fiber of the distributed optical fiber sensing system is laid on the rear surface of the soil chamber partition of the rectangular pipe jacking machine. The rear side of the soil chamber partition of the rectangular pipe jacking machine is the side that does not directly contact the soil.

[0058] In this embodiment, the electronic device receives the current stress data returned by the distributed optical fiber sensing system based on the data acquisition request, and can quickly identify strain fluctuations within the optical fiber monitoring range.

[0059] Please see Figure 2 , Figure 2 This is a flowchart illustrating the blind spot clearing method provided in this application embodiment. This method can be applied to electronic devices, which are connected to a distributed optical fiber sensing system. The sensing optical fiber of the distributed optical fiber sensing system is laid on the rear surface of the soil chamber partition of the rectangular pipe jacking machine.

[0060] like Figure 2 As shown, the blind spot clearing method provided in this application includes the following steps, detailed below:

[0061] S201, send a data acquisition request to the distributed fiber optic sensing system and receive the current stress data returned by the distributed fiber optic sensing system according to the data acquisition request;

[0062] The sensing fibers of the distributed fiber optic sensing system are deployed on the rear surface of the soil chamber partition of the rectangular pipe jacking machine. The rectangular pipe jacking machine is a trenchless construction machine designed specifically for the construction of underground rectangular channels or pipelines. Its core principle is to use a jacking device to push prefabricated pipe sections from the launching shaft to the receiving shaft section by section, while using a cutterhead to cut the soil and a screw conveyor or mud system to remove the soil, thereby achieving spatial replacement between the soil and the pipe sections.

[0063] refer to Figure 7 , Figure 7 This is a plan view of the rectangular pipe jacking machine used in the embodiments of this application. The gray area represents the blind zone outside the cutter head cutting trajectory.

[0064] refer to Figure 8 , Figure 8 A diagram of the optical fiber distribution network provided in the embodiments of this application.

[0065] The blind spot clearing method, prior to sending a data acquisition request to the distributed fiber optic sensing system and receiving the current stress data returned by the distributed fiber optic sensing system based on the data acquisition request, includes:

[0066] Obtain preset stress data and preset stress distribution map of the partition plate. Combine the preset stress data and preset stress distribution map of the partition plate into training samples. Combine different training samples into a training set. Use the training set to train the machine learning model to obtain the trained machine learning model.

[0067] S202, Input the current stress data into the visualization tool, and generate a stress distribution map of the soil chamber diaphragm through the visualization tool;

[0068] Among them, the stress distribution diagram of the soil silo is a graphic representation of the stress state of the soil silo. Its core is to reveal the stress distribution law of the silo under different working conditions through visualization.

[0069] S203, input the stress distribution map of the earth chamber partition into the trained machine learning model, and generate the load distribution on the front surface of the earth chamber partition through the trained machine learning model.

[0070] S204. Based on the load distribution on the front surface of the soil silo, obtain the pressure in the blind zone and the pressure in the non-blind zone of the area where the soil silo is located. Compare the pressure in the blind zone with the pressure in the non-blind zone to generate the ratio between the pressure in the blind zone and the pressure in the non-blind zone.

[0071] For example, based on the load distribution on the front surface of the soil silo, the pressure in the blind zone and the pressure in the non-blind zone of the area where the soil silo is located are obtained, and the ratio between the pressure in the blind zone and the pressure in the non-blind zone is calculated, including:

[0072] Input the load distribution on the front surface of the soil chamber baffle into the finite element analysis tool, and generate the pressure in the blind zone and the pressure in the non-blind zone of the area where the soil chamber baffle is located through the finite element analysis tool;

[0073] Obtain the pressure in the non-blind zone, compare the pressure in the blind zone with the pressure in the non-blind zone, and generate the ratio between the pressure in the blind zone and the pressure in the non-blind zone.

[0074] S205, when the ratio between the pressure in the blind zone and the pressure in the non-blind zone is greater than the activation threshold, the ratio is compared with a set value to obtain the comparison result. When the comparison result is that the ratio is greater than the activation threshold and less than the first proportion of the set value, a first cleaning decision is executed. When the ratio is not less than the first proportion of the set value and not greater than the second proportion of the set value, a second cleaning decision is executed. When the ratio is greater than the second proportion of the set value, a third cleaning decision is executed. The first cleaning decision is to only activate the outer nozzle of the dual-row nozzle to create eddies, which are used to flush the soil in the blind zone. The second cleaning decision is to activate the dual-row nozzle and control the outer and inner nozzles of the dual-row nozzle to spray conical water curtains in the medium-low pressure range. The third cleaning decision is to activate the dual-row nozzle and control the outer nozzle of the dual-row nozzle to spray conical water curtains in the medium-low pressure range, and control the inner nozzle of the dual-row nozzle to spray conical water curtains in the high pressure range. The conical water curtains in the medium-low pressure range are used to wash the soil in the blind zone, and the conical water curtains in the high pressure range are used to break up the soil in the blind zone.

[0075] Specifically, when the comparison result is a ratio greater than the activation threshold and less than a set value (first proportion), a first cleanup decision is executed, including:

[0076] When the comparison result is a ratio greater than the start threshold and less than the set value, the load distribution on the front surface of the soil chamber partition, the feature extraction information of the blind zone, and the number of nozzles are used as the query conditions for the current case. The query conditions for the current case are converted into the feature vector of the current case. The feature vector of the current case is submitted to the query engine of the vector database. The query engine performs a similarity search on the feature vector of the current case and generates search results. In the search results, the similarity between each historical case and the current case in the vector database is obtained. The case with the highest similarity is selected as the target case. The vector database stores the feature vector of each historical case. The feature extraction information of the blind zone includes the load distribution of the blind zone and the geometric feature vector of the blind zone.

[0077] Extract the preset water pressure, preset water volume, and preset deflection angle from the historical cleaning parameters stored in the target case. Select the preset water pressure, preset water volume, and preset deflection angle as the current water pressure, current water volume, and current deflection angle for the first cleaning decision. Encapsulate the current water pressure, current water volume, and current deflection angle of the first cleaning decision into a vortex creation instruction and send the vortex creation instruction to the execution mechanism.

[0078] Optionally, when the comparison result is a ratio greater than the activation threshold and less than a set value (first proportion), the load distribution on the front surface of the soil chamber baffle, the feature extraction information of the blind zone, and the number of nozzles are used as the query conditions for the current case. The query conditions for the current case are converted into the feature vector of the current case, and the feature vector of the current case is submitted to the query engine of the vector database. The query engine performs a similarity search on the feature vector of the current case to generate search results. In the search results, the similarity between each historical case and the current case in the vector database is obtained, and the case with the highest similarity is selected as the target case. The vector database stores the feature vector of each historical case. The feature extraction information of the blind zone includes the load distribution of the blind zone and the geometric feature vector of the blind zone, including:

[0079] The load distribution information, the geometric feature information of the blind zone of each historical case, and the execution parameters of each historical case are obtained. The feature vectors of the load distribution information, the geometric feature information of the blind zone of each historical case, and the execution parameters of each historical case are fused to generate the feature vector of each historical case. A vector database is constructed using the feature vectors of all historical cases.

[0080] When the comparison result is a ratio greater than the activation threshold and less than the set value, the load distribution on the front surface of the soil chamber partition, the feature extraction information of the blind zone, and the number of nozzles are used as the query conditions for the current case. The query conditions for the current case are converted into the feature vector of the current case. The feature vector of the current case is submitted to the query engine of the vector database. The query engine performs a similarity search on the feature vector of the current case and generates search results. In the search results, the similarity between each historical case and the current case in the vector database is obtained. The case with the highest similarity is selected as the target case. The vector database stores the feature vector of each historical case. The feature extraction information of the blind zone includes the load distribution of the blind zone and the geometric feature vector of the blind zone.

[0081] The number of nozzles refers to the total number of external and internal nozzles fixed on the earthwork partition.

[0082] Specifically, preset water pressure, preset water volume, and preset deflection angle are extracted from historical cleaning parameters stored in the target case. These preset water pressure, water volume, and deflection angle are selected as the current water pressure, water volume, and deflection angle for the first cleaning decision. The current water pressure, water volume, and deflection angle of the first cleaning decision are encapsulated into eddy current creation instructions, which are then sent to the execution mechanism. These instructions include:

[0083] Extract preset water pressure, preset water volume, and preset deflection angle from the historical cleanup parameters stored in the target case. Input the preset water pressure, preset water volume, and preset deflection angle into the simulation tool. The simulation tool generates the water flow velocity in the internal region of the vortex. The simulation tool is a numerical simulation tool based on the principle of fluid dynamics.

[0084] Based on the water flow velocity in the internal region of the vortex and the preset influence model, the influence radius of the vortex is generated. Based on the influence radius of the vortex, the influence area of ​​the vortex is generated. When the influence area of ​​the vortex is greater than the area in the feature extraction information of the blind zone, preset water pressure, preset water volume, and preset deflection angle are selected as the current water pressure, current water volume, and current deflection angle of the first cleaning decision. The current water pressure, current water volume, and current deflection angle of the first cleaning decision are encapsulated into the vortex creation instruction and sent to the execution mechanism.

[0085] Optionally, the influence area of ​​the eddy is generated based on the influence radius of the eddy, including: using the influence radius of the eddy as the radius of a circle, and using the formula for calculating the area of ​​a circle, multiplying pi by the square of the influence radius of the eddy to generate the influence area of ​​the eddy.

[0086] The value of pi is 3.14.

[0087] The preset water pressure, preset water volume, and preset deflection angle are extracted from the historical cleanup parameters stored in the target case. These preset water pressure, preset water volume, and preset deflection angle are then input into the simulation tool. The simulation tool generates the water flow velocity in the internal region of the vortex. The simulation tool is a numerical simulation tool based on fluid dynamics principles, including:

[0088] The cleanup process of the target case is divided into continuous data blocks with fixed time steps. For each data block, a lightweight numerical simulation model is established based on computational fluid dynamics principles to verify and evaluate the effectiveness of its cleanup parameters under the current working conditions. Data blocks with the best simulation results based on fluid dynamics principles are selected from the target case and dynamically combined into a new complete scheme. The water pressure, water volume, and deflection angle in the complete scheme are simulated using preset water pressure, preset water volume, and preset deflection angle simulation tools. The simulation tools are used to generate the water flow velocity in the internal region of the vortex. The influence model is defined as follows:

[0089] ;

[0090] ;

[0091] Indicates the radius of influence of the eddy current; Represents a constant; Indicates the radius of the nozzle;

[0092] This indicates the pressure difference between the nozzle outlet and the vortex. The greater the pressure difference between the nozzle outlet and the vortex, the stronger the rotational energy of the vortex; the smaller the pressure difference between the nozzle outlet and the vortex, the weaker the rotational energy of the vortex.

[0093] This indicates the average flow velocity at the nozzle exit. This represents the velocity difference between the average flow velocity at the nozzle outlet and the water flow velocity within the vortex's interior region.

[0094] Among them, the annular rotational characteristics of the vortex allow the water to flow tangentially along the corners, forming an annular scouring zone, which fully disturbs and softens the soil in the dead corners and blind spots. At the same time, the influence radius of the vortex can be adjusted. By matching the deflection angle of the nozzle, the vortex can be made to cover the corners and gaps, thus completely solving the scouring problem of rectangular cross sections.

[0095] The different levels are divided by a first ratio and a second ratio, wherein the first ratio and the second ratio are dynamically set according to the soil properties and jacking parameters.

[0096] Optionally, the first and second proportions are 50% and 75%, respectively;

[0097] Alternatively, the first and second proportions are 60% and 85% respectively;

[0098] Alternatively, the first and second proportions are 55% and 65% respectively.

[0099] Optionally, refer to Figure 6 , Figure 6 The following is a flowchart illustrating the application of the blind spot clearing method provided in this application embodiment, detailed below:

[0100] S601, the blind spot clearing procedure is started. A data acquisition request is sent to the distributed fiber optic sensing system. The current stress data returned by the distributed fiber optic sensing system according to the data acquisition request is received. The current stress data is input into the visualization tool. The visualization tool generates a stress distribution map of the soil chamber baffle. The stress distribution map of the soil chamber baffle is input into the trained machine learning model. The trained machine learning model generates the load distribution on the front surface of the soil chamber baffle. Based on the load distribution on the front surface of the soil chamber baffle, the pressure in the blind spot and the pressure in the non-blind spot of the area where the soil chamber baffle is located are obtained. The pressure in the blind spot is compared with the pressure in the non-blind spot to generate the ratio between the pressure in the blind spot and the pressure in the non-blind spot.

[0101] S602, when the ratio of the pressure in the blind zone to the pressure in the non-blind zone is greater than the activation threshold.

[0102] Compare the ratio with the set value to obtain the comparison result between the ratio and the set value;

[0103] S603, when the comparison result is that the ratio is greater than the activation threshold and less than 50% of the set value, only the outer nozzle of the dual-row nozzle is activated to create vortices, which are used to flush the soil in the blind zone.

[0104] S604, when the comparison result is greater than 50% of the set value and not greater than 75% of the set value, start the double-row nozzle, control the outer and inner nozzles of the double-row nozzle to spray a conical water curtain in the medium and low pressure range, and control the inner nozzle of the double-row nozzle to spray a conical water curtain in the high pressure range.

[0105] S605; When the comparison result is greater than 75% of the set value, activate the dual-row nozzles, controlling the outer nozzles of the dual-row nozzles to spray a conical water curtain within the medium-low pressure range, and controlling the inner nozzles of the dual-row nozzles to spray a conical water curtain within the high pressure range.

[0106] S606, check if the ratio between the pressure in the blind zone and the pressure in the non-blind zone is greater than the activation threshold; if yes, execute S602; otherwise, execute S607.

[0107] S607, Blind spot cleanup program turned off and data logging.

[0108] After the entire pipe jacking project is completed, the monitoring of the distributed optical fiber sensor network is stopped first, and the blind spot clearing decision system is shut down after ensuring that all monitoring data and working data are completely saved, encrypted and updated to the vector database.

[0109] The distributed fiber optic sensor network behind the soil silo does not need to be removed, and the nozzles on the pipe jacking machine can be reused in subsequent projects after passing inspection.

[0110] The beneficial effects of the embodiments of this application are as follows:

[0111] Firstly, when the ratio between the pressure in the blind zone and the pressure in the non-blind zone is greater than the activation threshold, the ratio is compared with a set value to obtain the comparison result. When the comparison result is that the ratio is greater than the activation threshold and less than the first proportion of the set value, a first cleaning decision is executed. When the ratio is not less than the first proportion of the set value and not greater than the second proportion of the set value, a second cleaning decision is executed. When the ratio is greater than the second proportion of the set value, a third cleaning decision is executed. Since the first, second, and third cleaning decisions are executed automatically without manual operation, the cleaning time of the blind zone is reduced, which is conducive to improving the cleaning efficiency of the blind zone.

[0112] Secondly, since the first cleaning decision only uses the outer nozzle of the double-row nozzle to create eddies, and the soil in the blind area is washed by the eddies, the first cleaning decision can clean the blind area in a gentler way, thereby reducing the disturbance to the strata. This is of great significance for protecting the ecological environment and reducing the impact of construction on the surrounding environment.

[0113] Please see Figure 3 , Figure 3 The flowchart for storing working data provided in the embodiments of this application is described in detail below:

[0114] S301: Obtain the working data of the rectangular pipe jacking machine, read the preset storage time, and determine whether the current time is the storage time;

[0115] S302, if the current time is the storage time, connect to the vector database and store the working data and current stress data in the vector database.

[0116] In this embodiment, connecting to a vector database and storing working data and current stress data in the vector database can effectively prevent the risk of losing working data and current stress data.

[0117] For the blind spot clearing method described in the above embodiments, please refer to [link / reference]. Figure 4 , Figure 4 This is a schematic block diagram of the blind spot clearing device provided in the embodiments of this application. Figure 4 The blind spot clearing device 400 shown can be applied to, for example... Figure 1 The application scenario diagram shows electronic devices. The following section uses electronic devices as an example to illustrate this. Figure 4 The blind spot clearing device 400 shown will be described in detail. The blind spot clearing device 400 may include a receiving module 401, a first input module 402, a second input module 403, a generating module 404, and a clearing module 405.

[0118] The receiving module 401 is used to send a data acquisition request to the distributed optical fiber sensing system and receive the current stress data returned by the distributed optical fiber sensing system according to the data acquisition request.

[0119] The first input module 402 is used to input the current stress data into the visualization tool and generate a stress distribution map of the soil chamber partition through the visualization tool;

[0120] The second input module 403 is used to input the stress distribution map of the soil chamber partition into the trained machine learning model, and generate the load distribution on the front surface of the soil chamber partition through the trained machine learning model.

[0121] The generation module 404 is used to obtain the pressure in the blind zone and the pressure in the non-blind zone of the area where the soil chamber partition is located based on the load distribution borne by the front surface of the soil chamber partition, compare the pressure in the blind zone with the pressure in the non-blind zone, and generate the ratio between the pressure in the blind zone and the pressure in the non-blind zone.

[0122] The cleaning module 405 is used to compare the ratio between the pressure in the blind zone and the pressure in the non-blind zone when the ratio is greater than a start-up threshold, and obtain the comparison result. If the ratio is greater than the start-up threshold but less than a first proportion of the set value, a first cleaning decision is executed. If the ratio is not less than the first proportion of the set value and not greater than a second proportion of the set value, a second cleaning decision is executed. If the ratio is greater than the second proportion of the set value, a third cleaning decision is executed. The first cleaning decision is to activate only the outer exhaust nozzle of the dual-row nozzle to create a vortex. The first cleaning decision is to activate the dual-row nozzles, controlling the outer and inner nozzles to spray a conical water curtain within the medium-low pressure range; the second cleaning decision is to activate the dual-row nozzles, controlling the outer nozzles to spray a conical water curtain within the medium-low pressure range, and controlling the inner nozzles to spray a conical water curtain within the high pressure range. The conical water curtain within the medium-low pressure range is used to wash the soil in the blind area, and the conical water curtain within the high pressure range is used to break up the soil in the blind area.

[0123] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0124] The beneficial effects of the embodiments of this application are as follows:

[0125] Firstly, when the ratio between the pressure in the blind zone and the pressure in the non-blind zone is greater than the activation threshold, the ratio is compared with a set value to obtain the comparison result. When the comparison result is that the ratio is greater than the activation threshold and less than the first proportion of the set value, a first cleaning decision is executed. When the ratio is not less than the first proportion of the set value and not greater than the second proportion of the set value, a second cleaning decision is executed. When the ratio is greater than the second proportion of the set value, a third cleaning decision is executed. Since the first, second, and third cleaning decisions are executed automatically without manual operation, the cleaning time of the blind zone is reduced, which is conducive to improving the cleaning efficiency of the blind zone.

[0126] Secondly, since the first cleaning decision only uses the outer nozzle of the double-row nozzle to create eddies, and the soil in the blind area is washed by the eddies, the first cleaning decision can clean the blind area in a gentler way, thereby reducing the disturbance to the strata. This is of great significance for protecting the ecological environment and reducing the impact of construction on the surrounding environment.

[0127] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0128] like Figure 5 As shown, Figure 5 The electronic device 2 includes: at least one processor 20, a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor 20, wherein the processor 20 executes the computer program 22 to implement the steps in any of the above method embodiments.

[0129] The electronic device 2 may include, but is not limited to, a processor 20 and a memory 21. Those skilled in the art will understand that... Figure 5 This is merely an example of electronic device 2 and does not constitute a limitation on electronic device 2. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0130] The processor 20 is used to run a computer program 22 stored in the memory 21, and performs the following steps when executing the computer program 22:

[0131] Send a data acquisition request to the distributed fiber optic sensing system and receive the current stress data returned by the distributed fiber optic sensing system based on the data acquisition request;

[0132] Input the current stress data into the visualization tool, and generate a stress distribution map of the soil chamber diaphragm using the visualization tool;

[0133] The stress distribution map of the earth chamber partition is input into the trained machine learning model, and the load distribution on the front surface of the earth chamber partition is generated by the trained machine learning model.

[0134] Based on the load distribution on the front surface of the earthwork partition, the pressure in the blind zone and the pressure in the non-blind zone of the area where the earthwork partition is located are obtained. The pressure in the blind zone is compared with the pressure in the non-blind zone to generate the ratio between the pressure in the blind zone and the pressure in the non-blind zone.

[0135] When the ratio between the pressure in the blind zone and the pressure in the non-blind zone is greater than the activation threshold, the ratio is compared with a set value to obtain the comparison result. If the comparison result is that the ratio is greater than the activation threshold and less than the first proportion of the set value, a first cleaning decision is executed. If the ratio is not less than the first proportion of the set value and not greater than the second proportion of the set value, a second cleaning decision is executed. If the ratio is greater than the second proportion of the set value, a third cleaning decision is executed. The first cleaning decision is to activate only the outer nozzle of the dual-row nozzle to create eddies, which are used to flush the soil in the blind zone. The second cleaning decision is to activate the dual-row nozzle and control the outer and inner nozzles of the dual-row nozzle to spray conical water curtains within the medium-low pressure range. The third cleaning decision is to activate the dual-row nozzle and control the outer nozzle of the dual-row nozzle to spray conical water curtains within the medium-low pressure range, and control the inner nozzle of the dual-row nozzle to spray conical water curtains within the high pressure range. The conical water curtains within the medium-low pressure range are used to wash the soil in the blind zone, and the conical water curtains within the high pressure range are used to break up the soil in the blind zone.

[0136] The processor 20 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors, field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0137] In some embodiments, the memory 21 may be an internal storage unit of the electronic device 2, such as a hard disk or memory of the electronic device 2. In other embodiments, the memory 21 may be an external storage device of the electronic device 2, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on the electronic device 2.

[0138] Furthermore, the memory 21 may include both internal storage units and external storage devices of the electronic device 2. The memory 21 is used to store the operating system, applications, boot loader, data, and other programs, such as the program code of the computer program. The memory 21 can also be used to temporarily store data that has been output or will be output.

[0139] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0140] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0141] Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium includes: an entity or device for carrying computer program code to an electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium.

[0142] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0143] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for clearing blind spots based on the stress of earthwork diaphragms, characterized in that, Applied to electronic devices, the electronic devices are connected to a distributed fiber optic sensing system. The sensing fibers of the distributed fiber optic sensing system are deployed on the rear surface of the soil chamber partition of a rectangular pipe jacking machine. The blind spot clearing method includes: Send a data acquisition request to the distributed fiber optic sensing system and receive the current stress data returned by the distributed fiber optic sensing system based on the data acquisition request; Input the current stress data into the visualization tool, and generate a stress distribution map of the soil chamber diaphragm using the visualization tool; The stress distribution map of the earth chamber partition is input into the trained machine learning model, and the load distribution on the front surface of the earth chamber partition is generated by the trained machine learning model. Based on the load distribution on the front surface of the soil silo, the pressure in the blind zone and the pressure in the non-blind zone of the area where the soil silo is located are obtained. The pressure in the blind zone is compared with the pressure in the non-blind zone to generate a ratio between the pressure in the blind zone and the pressure in the non-blind zone. When the ratio between the pressure in the blind zone and the pressure in the non-blind zone is greater than the activation threshold, the ratio is compared with a set value to obtain the comparison result between the ratio and the set value. When the comparison result is that the ratio is greater than the activation threshold and less than the first proportion of the set value, a first cleanup decision is executed. When the ratio is not less than the first proportion of the set value and not greater than the second proportion of the set value, a second cleanup decision is executed. When the ratio is greater than the second proportion of the set value, a third cleanup decision is executed. The first cleanup decision was to use only the outer nozzle of the dual-row nozzle to create vortices, which were then used to flush the soil in the blind spots. The second cleaning decision is to activate the dual-row nozzles and control the outer and inner nozzles of the dual-row nozzles to spray out a cone-shaped water curtain at a medium-low pressure level. The third cleaning decision is to activate the dual-row nozzles, control the outer nozzle of the dual-row nozzles to spray out a cone-shaped water curtain in the medium and low pressure range, and control the inner nozzle of the dual-row nozzles to spray out a cone-shaped water curtain in the high pressure range. The cone-shaped water curtain in the medium and low pressure range is used to wash the soil in the blind area, and the cone-shaped water curtain in the high pressure range is used to break up the soil in the blind area. Specifically, when the comparison result is a ratio greater than the activation threshold and less than a set value (first proportion), a first cleanup decision is executed, including: When the comparison result is a ratio greater than the start threshold and less than the set value, the load distribution on the front surface of the soil chamber partition, the feature extraction information of the blind zone, and the number of nozzles are used as the query conditions for the current case. The query conditions for the current case are converted into the feature vector of the current case. The feature vector of the current case is submitted to the query engine of the vector database. The query engine performs a similarity search on the feature vector of the current case and generates search results. In the search results, the similarity between each historical case and the current case in the vector database is obtained. The case with the highest similarity is selected as the target case. The vector database stores the feature vector of each historical case. The feature extraction information of the blind zone includes the load distribution of the blind zone and the geometric feature vector of the blind zone. Extract the preset water pressure, preset water volume, and preset deflection angle from the historical cleaning parameters stored in the target case. Select the preset water pressure, preset water volume, and preset deflection angle as the current water pressure, current water volume, and current deflection angle for the first cleaning decision. Encapsulate the current water pressure, current water volume, and current deflection angle of the first cleaning decision into a vortex creation instruction and send the vortex creation instruction to the execution mechanism.

2. The blind spot clearing method according to claim 1, characterized in that, Extract preset water pressure, preset water volume, and preset deflection angle from the historical cleaning parameters stored in the target case. Select these preset water pressure, preset water volume, and preset deflection angle as the current water pressure, current water volume, and current deflection angle for the first cleaning decision. Encapsulate the current water pressure, current water volume, and current deflection angle of the first cleaning decision into eddy current creation instructions and send these instructions to the execution mechanism. The instructions include: The preset water pressure, preset water volume, and preset deflection angle are extracted from the historical cleanup parameters stored in the target case. These preset water pressure, preset water volume, and preset deflection angle are then input into the simulation tool. The simulation tool generates the water flow velocity in the internal region of the vortex. The simulation tool is a numerical simulation tool based on the principles of fluid dynamics.

3. The blind spot clearing method according to claim 1, characterized in that, After the blind spot clearing decision is executed when the ratio between the pressure in the blind spot and the pressure in the non-blind spot is greater than the activation threshold, the blind spot clearing method includes: Acquire the working data of the rectangular pipe jacking machine, read the preset storage time, and determine whether the current time is the storage time; If the current time is the storage time, connect to the vector database and store the working data and current stress data in the vector database.

4. The blind spot clearing method according to claim 1, characterized in that, Before sending a data acquisition request to the distributed fiber optic sensing system and receiving the current stress data returned by the distributed fiber optic sensing system based on the data acquisition request, the blind spot clearing method includes: Obtain preset stress data and preset stress distribution map of the partition plate. Combine the preset stress data and preset stress distribution map of the partition plate into training samples. Combine different training samples into a training set. Use the training set to train the machine learning model to obtain the trained machine learning model.

5. The blind spot clearing method according to claim 1, characterized in that, The first and second proportions are 50% and 75% respectively; Alternatively, the first and second proportions are 60% and 85% respectively; Alternatively, the first and second proportions are 55% and 65% respectively.

6. A blind spot cleaning device based on the stress of a soil silo baffle, based on the blind spot cleaning method according to any one of claims 1 to 5, characterized in that, Applied to electronic equipment, the electronic equipment connects to a distributed fiber optic sensing system. The sensing fibers of the distributed fiber optic sensing system are deployed on the rear surface of the soil chamber partition of the rectangular pipe jacking machine, including: The receiving module is used to send a data acquisition request to the distributed fiber optic sensing system and receive the current stress data returned by the distributed fiber optic sensing system based on the data acquisition request. The first input module is used to input the current stress data into the visualization tool, and the visualization tool generates a stress distribution map of the soil chamber diaphragm. The second input module is used to input the stress distribution map of the soil chamber partition into the trained machine learning model, and generate the load distribution on the front surface of the soil chamber partition through the trained machine learning model. The generation module is used to obtain the pressure in the blind zone and the pressure in the non-blind zone of the area where the soil silo is located based on the load distribution on the front surface of the soil silo. The pressure in the blind zone is compared with the pressure in the non-blind zone to generate the ratio between the pressure in the blind zone and the pressure in the non-blind zone. The cleaning module is used to compare the ratio between the pressure in the blind zone and the pressure in the non-blind zone when the ratio is greater than the activation threshold, obtain the comparison result between the ratio and the set value, and execute a first cleaning decision when the ratio is greater than the activation threshold and less than the set value in a first proportion. When the ratio is not less than the first proportion of the set value and not greater than the second proportion of the set value, a second cleaning decision is executed. When the ratio is greater than the second proportion of the set value, a third cleaning decision is executed. The first cleanup decision was to use only the outer nozzle of the dual-row nozzle to create vortices, which were then used to flush the soil in the blind spots. The second cleaning decision is to activate the dual-row nozzles and control the outer and inner nozzles of the dual-row nozzles to spray out a cone-shaped water curtain at a medium-low pressure level. The third cleaning decision is to activate the dual-row nozzles, control the outer nozzle of the dual-row nozzles to spray a cone-shaped water curtain in the medium-low pressure range, and control the inner nozzle of the dual-row nozzles to spray a cone-shaped water curtain in the high pressure range. The cone-shaped water curtain in the medium-low pressure range is used to wash the soil in the blind area, and the cone-shaped water curtain in the high pressure range is used to break up the soil in the blind area.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the blind spot clearing method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the blind spot clearing method as described in any one of claims 1 to 5.

Images