Safety early warning method and system for tunneling work

Abstract

The invention discloses a safety early warning method and system for tunneling work, and relates to the technical field of tunneling safety early warning. The method comprises the following steps: constructing a stratigraphic environment basic twinborn model; recognizing the position and morphological characteristics of the obstacle; the obstacle position and morphological characteristics are input into an obstacle decoupling model library for decoupling search, and a matched obstacle twin model is output; taking the matched obstacle twinborn model as a plug-in, fusing the matched obstacle twinborn model into the stratum environment basic twinborn model in the same coordinate system, and obtaining a fused twinborn model; and performing obstacle area risk analysis according to the fusion twin model, outputting a risk early warning signal, and feeding back the risk early warning signal to the tunneling equipment for risk control. The technical problems of resource waste and low efficiency caused by independent modeling in underground tunneling work in the prior art are solved, and the technical effects of saving resources and improving the safety and efficiency of tunneling work by sharing the underground environment twinborn basic model and only inserting the obstacle twinborn model are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of tunneling safety warning, and particularly relates to a safety warning method and system for tunneling work. Background Art

[0002] During the tunneling construction process, the frequent occurrence of underground construction obstacles (such as existing tunnels, underground pipelines, relics of civil air defense projects, etc.) is one of the core problems affecting construction safety. These obstacles are scattered and have various forms, and it is often difficult to comprehensively and accurately grasp information such as their positions, burial depths, and internal structures. The traditional tunneling safety warning method has significant limitations. For each tunneling area, independent formation detection and obstacle modeling work need to be carried out, which not only consumes a large amount of human, material, and time costs, resulting in serious waste of resources, but also is not conducive to systematic expansion and rapid deployment. How to achieve rapid model construction and deployment of obstacles in front of tunneling in a complex and changeable underground environment has become a key technical bottleneck for ensuring the safe and efficient progress of tunneling work. Summary of the Invention

[0003] This application provides a safety warning method and system for tunneling work, which solves the technical problem of resource waste and low efficiency caused by the need for separate modeling in underground tunneling work in the prior art.

[0004] In the first aspect of this application, a safety warning method for tunneling work is provided. The method includes: Based on the formation detection and modeling data of the first tunneling work area uploaded by the cloud service terminal, a basic twin model of the formation environment is constructed; a multi-source sensing device is used to identify the position and morphological characteristics of obstacles in front of the tunneling equipment, wherein the multi-source sensing device is embedded in the tunneling equipment, and the tunneling equipment is in the first tunneling work area; the position and morphological characteristics of the obstacles are input into the obstacle decoupling model library for decoupling search, and a matching obstacle twin model is output, and the obstacle decoupling model library is embedded in the cloud service terminal; the matching obstacle twin model is used as a plug-in and fused into the basic twin model of the formation environment in the same coordinate system to obtain a fused twin model; risk analysis of the obstacle area is carried out according to the fused twin model, and a risk warning signal is output, and the risk warning signal is fed back to the tunneling equipment for risk control.

[0005] Further, the method of inputting the position and morphological characteristics of the obstacles into the obstacle decoupling model library for decoupling search includes: obtaining underground obstacle samples by the cloud service terminal; identifying the parameterized model templates corresponding to the underground obstacle samples respectively, and constructing the obstacle decoupling model library; inputting the position and morphological characteristics of the obstacles into the obstacle decoupling model library for decoupling search with each parameterized model template, and obtaining a parameterized model template with both the position similarity and the morphological similarity greater than a preset threshold.

[0006] Further, perform obstacle area risk analysis according to the fusion twin model and output risk warning signals. The method includes: performing obstacle area risk analysis on the tunneling parameters of the tunneling equipment according to the fusion twin model, including collision risk, sudden change in resistance risk, tunneling attitude deviation risk, and structural deformation risk; calculating risks according to the collision risk, sudden change in resistance risk, tunneling attitude deviation risk, and structural deformation risk, and outputting tunneling risk indicators; determining risk levels according to the tunneling risk indicators and outputting risk warning signals corresponding to the risk levels.

[0007] Further, feedback the risk warning signals to the tunneling equipment for risk control. The method includes: recording the tunneling parameters of the tunneling equipment, where the tunneling parameters include the propulsion path, propulsion rate, and cutter head rotation speed; when the tunneling equipment receives the risk warning signals, perform gradient optimization control on the tunneling parameters to minimize the tunneling risk indicators, and obtain optimized tunneling parameters. Among them, the priority of adaptive optimization control is cutter head rotation speed > propulsion rate > propulsion path; control the tunneling of the tunneling equipment according to the optimized tunneling parameters.

[0008] Further, the cloud service terminal is distributedly connected to multiple tunneling equipment. The method further includes: detecting multiple tunneling working areas corresponding to the multiple tunneling equipment; identifying N tunneling equipment in the first tunneling working area, collecting N formation detection and modeling data corresponding to the N tunneling equipment, and uploading the N formation detection and modeling data to the cloud service terminal to synchronously update the formation environment basic twin model.

[0009] Further, upload the N formation detection and modeling data to the cloud service terminal to synchronously update the obstacle decoupling model library. The method includes: identifying N groups of obstacle positions and morphological features corresponding to the N formation detection and modeling data; obtaining N return results corresponding to the N groups of obstacle positions and morphological features in the obstacle decoupling model library, and collecting M groups of obstacle positions and morphological features with empty return results, where M is a positive integer less than or equal to N; using the M groups of obstacle positions and morphological features as incremental data to update the obstacle decoupling model library.

[0010] Further, the multi-source perception device includes at least any two of an inertial navigation unit, a visual camera, an infrared / structured light depth camera, and a lidar.

[0011] Further, to identify the parametric model templates corresponding to the underground obstacle samples respectively, the method includes: collecting three-dimensional point cloud data samples of the underground obstacle samples; extracting the corresponding position feature samples and morphological feature samples of the three-dimensional point cloud data samples, where the morphological features include geometric features and material features; constructing an obstacle parametric model template according to the position feature samples and morphological feature samples corresponding to the three-dimensional point cloud data samples.

[0012] Further, to identify the parametric model templates corresponding to the underground obstacle samples respectively and construct the obstacle decoupling model library, the method further includes: decomposing each underground obstacle sample according to its structural function to obtain multiple obstacle components; generating an underground component obstacle model template corresponding to the underground obstacle sample according to the multiple obstacle components. When a new underground obstacle sample is added, obtaining the required obstacle components corresponding to the new underground obstacle sample; combining the required obstacle components from the underground component obstacle model templates to update the obstacle decoupling model library.

[0013] In the second aspect of the present application, a safety warning system for tunneling work is provided. The system includes: A model construction module, configured to construct a basic twin model of the stratum environment based on the stratum exploration modeling data uploaded by the cloud service terminal in the first tunneling work area; an identification module, configured to use a multi-source sensing device to identify the position and morphological features of obstacles in front of the tunneling equipment, where the multi-source sensing device is embedded in the tunneling equipment and the tunneling equipment is in the first tunneling work area; a search module, configured to input the obstacle position and morphological features into the obstacle decoupling model library for decoupling search and output a matching obstacle twin model, and the obstacle decoupling model library is embedded in the cloud service terminal; a fusion module, configured to use the matching obstacle twin model as a plug-in to fuse it into the basic twin model of the stratum environment in the same coordinate system to obtain a fused twin model; an analysis module, configured to perform risk analysis on the obstacle area according to the fused twin model, output a risk warning signal, and feedback the risk warning signal to the tunneling equipment for risk control.

[0014] One or more technical solutions provided in the present application have at least the following technical effects or advantages: The present application solves the technical problem in the prior art that separate modeling is required in underground tunneling work, resulting in resource waste and low efficiency, and achieves the technical effect of saving resources and improving the safety and efficiency of tunneling operations by sharing the basic twin model of the underground environment and only inserting the obstacle twin model. Description of the Drawings

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0016] Figure 1 Schematic flow diagram of a safety warning method for tunneling work provided by an embodiment of the present application; Figure 2 Schematic structural diagram of a safety warning system for tunneling work provided by an embodiment of the present application.

[0017] Explanation of reference numerals: model construction module 11, identification module 12, search module 13, fusion module 14, analysis module 15. Detailed implementation manners

[0018] By providing a safety warning method and system for tunneling work, the present application solves the technical problems of resource waste and low efficiency caused by the need for separate modeling in underground tunneling work in the prior art.

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0020] It should be noted that the terms "include" and "have" are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server that includes a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0021] Embodiment 1, as Figure 1 shown, the present application provides a safety warning method for tunneling work, wherein the method includes: Based on the stratum detection modeling data uploaded by the cloud service terminal in the first tunneling work area, a basic stratum environment twin model is constructed.

[0022] In the embodiment of the present application, through sensors and measuring devices, the stratum detection data of the first tunneling work area is collected, including various physical properties such as the distribution, hardness, and humidity of the soil layer, and the stratum detection modeling data is generated; after receiving these data, the cloud service terminal uploads them to the cloud for processing to generate a basic stratum environment twin model to reflect the basic underground environment.

[0023] Furthermore, the cloud service terminal is distributedly connected to multiple tunneling devices, and further includes: Detect multiple tunneling working areas corresponding to the multiple tunneling devices; identify N tunneling devices in the first tunneling working area, collect N formation detection and modeling data corresponding to the N tunneling devices, and upload the N formation detection and modeling data to the cloud service terminal to synchronously update the formation environment basic twin model.

[0024] In the embodiment of the present application, the cloud service terminal is distributedly connected to multiple tunneling devices, and the cloud service terminal exchanges data with the multiple tunneling devices through a wireless communication network to ensure that the working state information of each tunneling device and its surrounding environment data can be received in real time; each tunneling device collects formation detection data of the corresponding working area through a variety of sensors configured thereon, including but not limited to physical parameters such as soil layer distribution, rock mass characteristics, water level changes, and underground structures.

[0025] When multiple tunneling devices are working simultaneously, the cloud service terminal will detect and identify the specific working area where each tunneling device is located to ensure that the data collected by all devices belongs to the corresponding area. According to the identified position of the tunneling device, the cloud service terminal will assign a corresponding working area label to each tunneling device and collect the formation detection and modeling data corresponding to the device. The cloud service terminal uploads this formation detection and modeling data to the cloud for processing. After receiving the data, the cloud server performs unified data fusion and processing, analyzes key information such as the soil layer characteristics and obstacle positions in the area where each tunneling device is located, and synchronously updates this information to the formation environment basic twin model, so as to ensure that the formation environment basic twin model always remains up-to-date and reflects the real-time underground working environment and its changes.

[0026] Furthermore, uploading the N formation detection and modeling data to the cloud service terminal to synchronously update the obstacle decoupling model library includes: Identify N groups of obstacle positions and morphological characteristics corresponding to the N formation detection and modeling data; obtain N return results corresponding to the N groups of obstacle positions and morphological characteristics in the obstacle decoupling model library, collect M groups of obstacle positions and morphological characteristics with empty return results, where M is a positive integer less than or equal to N; use the M groups of obstacle positions and morphological characteristics as incremental data to update the obstacle decoupling model library.

[0027] The cloud service terminal receives N formation detection and modeling data from multiple tunneling devices, analyzes these data through a data processing system, and identifies the corresponding obstacle positions and morphological features in each set of formation detection data. These features may include information such as the spatial position, shape, and size of the obstacles. The cloud service terminal searches in the obstacle decoupling model library, and based on the obstacle positions and morphological features corresponding to each set of formation detection data, searches for and matches existing obstacle models. If a corresponding obstacle matching result is found in the model library, the system will return relevant information; if no result can be matched, the cloud service terminal will mark this set of data as having no matching result. M sets of obstacle positions and morphological features with empty return results (where M is a positive integer less than or equal to N) will be identified as new or unknown obstacle information. Taking these M sets of obstacle positions and morphological features with no matching results as incremental data, the cloud service terminal will add them to the obstacle decoupling model library. In this way, the obstacle decoupling model library can be dynamically updated, gradually accumulating obstacle models, thereby enhancing its ability to identify new obstacles. The updated obstacle decoupling model library will contain the latest obstacle information, enabling subsequent tunneling operations to make decisions using more comprehensive and accurate obstacle data, further improving the safety and efficiency of tunneling work.

[0028] Use multi-source sensing devices to identify the positions and morphological features of obstacles in front of the tunneling device, where the multi-source sensing devices are embedded in the tunneling device, and the tunneling device is in the first tunneling work area.

[0029] Furthermore, the multi-source sensing devices at least include any two of an inertial navigation unit, a visual camera, an infrared / structured light depth camera, and a lidar.

[0030] In the embodiment of the present application, the multi-source sensing devices are embedded in the tunneling device. When the tunneling device is in the first tunneling work area, these embedded sensing devices identify the positions and morphological features of the obstacles in front through real-time data collection. The multi-source sensing devices at least include any two of an inertial navigation unit, a visual camera, an infrared / structured light depth camera, and a lidar; the inertial navigation unit monitors the dynamic state of the tunneling device, such as acceleration and rotation angle, provides the movement trajectory and position change information of the device, and helps to judge the relative position of the obstacle; the visual camera can identify the morphological, color, and texture features of the obstacle through image collection and computer vision technology, providing detailed appearance information for environmental perception; the infrared / structured light depth camera accurately obtains the depth information of the obstacle through infrared imaging or structured light technology, helping to perform three-dimensional space scanning in low light or complex environments; the lidar generates high-precision point cloud data through laser scanning, measures the distance, shape, and position of the obstacle, and provides a three-dimensional geometric description of the obstacle.

[0031] Input the obstacle position and morphological features into the obstacle decoupling model library for decoupling search, and output the matching obstacle twin model. The obstacle decoupling model library is embedded in the cloud service terminal.

[0032] The cloud service terminal receives the obstacle position and morphological feature data obtained from multi-source perception devices. These data capture the spatial position, shape, and other features of the obstacle through sensors, covering the detailed information of the obstacle in the tunneling work area. The cloud service terminal inputs these data into the obstacle decoupling model library for decoupling search, and uses the obstacle decoupling model library to analyze and match the input obstacle data. Each obstacle twin model in the obstacle decoupling model library represents the characteristics of a specific type of obstacle, including parameters such as its position, morphology, size, and material. Through decoupling search, the system can quickly compare the input obstacle position and morphological features with the stored obstacle twin models and output the matching obstacle twin model.

[0033] Furthermore, inputting the obstacle position and morphological features into the obstacle decoupling model library for decoupling search includes: Obtain underground obstacle samples by the cloud service terminal; identify the parameterized model templates corresponding to the underground obstacle samples respectively, and construct the obstacle decoupling model library; input the obstacle position and morphological features into the obstacle decoupling model library to perform decoupling search with each parameterized model template, and obtain the parameterized model templates whose position similarity and morphological similarity are both greater than the preset threshold.

[0034] The cloud service terminal obtains underground obstacle samples from multiple tunneling devices. These samples are obstacle data collected by perception devices, including features such as the position, morphology, size, and material of the obstacle. Through detailed analysis of the obstacle samples, geometric features, surface characteristics, and other key parameters of the obstacle are extracted to construct parameterized model templates. Among them, the parameterized model template provides a standardized model description for each type of obstacle; the parameterized model template is stored in the database to obtain the obstacle decoupling model library.

[0035] The cloud service terminal inputs the real-time collected obstacle position and morphological features into the obstacle decoupling model library and performs decoupling search in combination with the parameterized model templates.

[0036] By matching the collected obstacle data with each pre - constructed parametric model template in the obstacle decoupling model library, that is, by comparing the input obstacle features with the obstacle models stored in the template, the matching degree is determined. Specifically, the position similarity is obtained by calculating the position difference between the spatial position of the input obstacle and the position of the obstacle in each template; the position similarity can be calculated by Euclidean distance or other geometric distance measurement methods, that is, by measuring the distance between the coordinates of the input obstacle and the coordinates of the template obstacle. Among them, a smaller distance value indicates a higher similarity. The shape similarity is calculated by comparing the shape and size differences of the obstacles. Shape - matching algorithms such as contour analysis, geometric transformation, or point - cloud data comparison can be used to evaluate the shape differences between the input obstacle and the template. Finally, the calculated position similarity and shape similarity are compared with a preset threshold; if both of these similarities are greater than the predetermined threshold, it is considered that the input obstacle highly matches a certain template obstacle, and the corresponding parametric model template is returned.

[0037] Furthermore, identifying the parametric model templates corresponding to the underground obstacle samples respectively includes: Collecting the three - dimensional point - cloud data samples of the underground obstacle samples; extracting the corresponding position - feature samples and shape - feature samples from the three - dimensional point - cloud data samples, where the shape features include geometric features and material features; constructing the obstacle parametric model template according to the position - feature samples and shape - feature samples corresponding to the three - dimensional point - cloud data samples.

[0038] Collecting the three - dimensional point - cloud data samples of the underground obstacle samples through the lidar and structured - light depth camera on the tunneling equipment. The three - dimensional point - cloud data samples contain the spatial distribution and three - dimensional shape of the obstacles. Extracting the corresponding position - feature samples and shape - feature samples from the three - dimensional point - cloud data samples. The position features include the central position, boundary position, etc. of the obstacles; the shape features include geometric features and material features; the geometric features such as the shape, size, surface contour, etc. of the obstacles, and the material features include the material type of the obstacles (such as rock, soil, etc.) and its surface properties (such as hardness, roughness, etc.). Constructing the parametric model template of the obstacles according to the extracted position - feature samples and shape - feature samples of the three - dimensional point - cloud data samples. This template provides a standardized way of describing obstacles by transforming the geometric shape and material characteristics of the obstacles into a parametric mathematical model.

[0039] Furthermore, identifying the parametric model templates corresponding to the underground obstacle samples respectively and constructing the obstacle decoupling model library also includes: Decompose each underground obstacle sample according to its structural function to obtain multiple obstacle components; generate an underground component obstacle model template corresponding to the underground obstacle sample according to the multiple obstacle components. When a new underground obstacle sample is added, obtain the required obstacle components corresponding to the new underground obstacle sample; combine the required obstacle components from the underground component obstacle model template to update the obstacle decoupling model library.

[0040] Preferably, decompose each underground obstacle sample according to its structural function to obtain multiple obstacle components. For example, an underground obstacle may contain multiple layers of different materials, such as rock formations, soil, pipelines, or support structures. According to the extracted multiple obstacle components, generate an underground component obstacle model template corresponding to the underground obstacle sample. These underground component obstacle model templates describe the functional and structural characteristics of each component in a standardized manner. When a new underground obstacle sample is added, analyze the new sample to identify its corresponding required obstacle components; if the new obstacle sample contains new components, determine the characteristics of these components and generate corresponding model templates. Combine the required obstacle components from the underground component obstacle model template to update the obstacle decoupling model library. By combining the newly added required obstacle components with the components in the existing model library, generate a new obstacle decoupling model and store these updated models in the obstacle decoupling model library.

[0041] Take the matching obstacle twin model as a plug-in and fuse it into the formation environment basic twin model in the same coordinate system to obtain a fused twin model.

[0042] In the embodiment of the present application, convert the matching obstacle twin model into a standardized plug-in format and accurately fuse it into the formation environment basic twin model according to the position and size of the matching obstacle twin model in the three-dimensional space, so as to obtain a fused twin model. By fusing the obstacle twin model as a plug-in with the formation environment basic twin model in a unified coordinate system, a fused twin model containing all environmental and obstacle data is generated.

[0043] Conduct risk analysis of the obstacle area according to the fused twin model, output a risk warning signal, and feedback the risk warning signal to the tunneling equipment for risk control.

[0044] The system conducts a comprehensive analysis of the tunneling operation area based on the integrated twin model, identifies the location and shape of obstacles, calculates and evaluates potential risk types, such as collision risk, sudden change in resistance risk, tunneling attitude deviation risk, and structural deformation risk. Then, the system calculates the tunneling risk indicators according to the risk types, quantifies the severity of each risk, determines the risk level based on the preset threshold, and outputs the corresponding risk warning signals. Finally, the risk warning signals are fed back to the tunneling equipment, and the control system adjusts the tunneling parameters, such as the propulsion path, propulsion rate, and cutterhead speed, according to the warning signals, so as to optimize the tunneling operation, avoid the occurrence of safety accidents, and ensure the safety and efficiency of the operation process.

[0045] Furthermore, the risk analysis of the obstacle area is carried out according to the integrated twin model, and the risk warning signals are output, including: Conduct a risk analysis of the tunneling parameters of the tunneling equipment for the obstacle area according to the integrated twin model, including collision risk, sudden change in resistance risk, tunneling attitude deviation risk, and structural deformation risk; calculate the tunneling risk indicators according to the collision risk, sudden change in resistance risk, tunneling attitude deviation risk, and structural deformation risk, and output the tunneling risk indicators; determine the risk level according to the tunneling risk indicators, and output the risk warning signals corresponding to the risk level.

[0046] Based on the integrated twin model, the system conducts a risk analysis of the tunneling parameters of the tunneling equipment for the obstacle area, including collision risk, sudden change in resistance risk, tunneling attitude deviation risk, and structural deformation risk. The system comprehensively evaluates the environment of the current working area of the tunneling equipment by using the formation environment data and obstacle information integrated in the integrated twin model.

[0047] Based on the formation environment and obstacle data integrated in the fusion twin model, the system calculates various types of risks separately. For collision risk, the system calculates the possible collision danger by using a collision prediction algorithm through evaluating the distance between the current tunneling equipment and the obstacles ahead, the morphological characteristics of the obstacles, and their relative positions with the tunneling equipment; when the equipment approaches the obstacles, the collision risk index is dynamically adjusted according to the changes in distance and morphological characteristics. For the risk of sudden resistance change, the system calculates based on the physical properties of the formation (such as soil density, hardness, humidity, etc.) and evaluates the soil changes encountered during the advancement of the tunneling equipment; when the tunneling equipment encounters a sharp change in soil hardness or density, the system analyzes the mechanical properties of the formation, calculates the risk of sudden resistance change, and generates the corresponding resistance risk index. For the risk of tunneling attitude deviation, the system monitors the motion state of the tunneling equipment, including parameters such as the advancement path, advancement rate, and equipment inclination; when the equipment has an abnormal attitude deviation (such as excessive inclination or vibration), the system calculates the deviation risk through sensor data and outputs the corresponding risk value according to the deviation angle and rate. For the risk of structural deformation, the system analyzes the possible deformation of the underground structure (such as tunnel walls, support frames, etc.) during tunneling; the system calculates the risk of underground structure deformation through the stress-strain data of the soil, combined with the pressure data of the tunneling equipment, and outputs the risk index of structural deformation. By combining the values of collision risk, sudden resistance change risk, tunneling attitude deviation risk, and structural deformation risk according to weights, the system finally calculates the tunneling risk index, which comprehensively reflects the safety status of the current tunneling operation. The higher the value, the greater the risk, and the lower the value, the safer the operation.

[0048] The system determines the risk level according to the obtained tunneling risk index; the risk level is divided according to the numerical range of the risk index, and may include low risk, medium risk, and high risk levels. The system matches the tunneling risk index with the risk level according to the set threshold to determine the severity of the risk. The system outputs a risk warning signal corresponding to the risk level. This signal is used to indicate the risk level currently faced by the tunneling equipment, and the signal content includes specific risk types, levels, and corresponding warning measures. After receiving the risk warning signal, the tunneling equipment can take corresponding control measures according to the risk level, such as adjusting the advancement path, reducing the advancement rate, or optimizing the cutterhead rotation speed, so as to adopt appropriate risk control strategies at different risk levels to ensure the safety and efficiency of the tunneling operation.

[0049] Furthermore, feeding back the risk warning signal to the tunneling equipment for risk control includes: Record the tunneling parameters of the tunneling equipment, where the tunneling parameters include the propulsion path, propulsion rate, and cutterhead rotation speed; when the tunneling equipment receives the risk warning signal, perform gradient optimization control on the tunneling parameters to minimize the tunneling risk index, and obtain optimized tunneling parameters. Among them, the priority of the adaptive optimization control is cutterhead rotation speed > propulsion rate > propulsion path; control the tunneling of the tunneling equipment according to the optimized tunneling parameters.

[0050] During tunneling, record the tunneling parameters of the tunneling equipment, which include the propulsion path, propulsion rate, and cutterhead rotation speed. The propulsion path refers to the travel route of the tunneling equipment in the underground operation area, the propulsion rate is the distance advanced by the tunneling equipment per unit time, and the cutterhead rotation speed is the rotation speed of the cutterhead of the tunneling equipment.

[0051] When the tunneling equipment receives a risk warning signal from the system, the system will start a gradient optimization control algorithm based on the goal of minimizing the tunneling risk index. This optimization algorithm will adjust the tunneling parameters according to the risk level feedback in the risk warning signal to reduce potential risks. For example, when the collision risk is high, the system may give priority to reducing the cutterhead rotation speed to avoid collisions caused by high-speed rotation. Similarly, when the risk of sudden resistance change is high, the system will adjust the propulsion rate to reduce the possibility of the tunneling equipment encountering excessive resistance. The system will gradually adjust the propulsion path, propulsion rate, and cutterhead rotation speed according to the severity of various risks. During the optimization process, the system sets the priority of the adaptive optimization control, where the priority of the cutterhead rotation speed is the highest, followed by the propulsion rate, and finally the propulsion path. The system controls the tunneling process of the tunneling equipment according to the optimized tunneling parameters. After gradient optimization, the tunneling equipment will automatically adjust its propulsion path, rate, and cutterhead rotation speed to achieve the optimal operating state, minimize risks to the greatest extent, and ensure the smooth progress of the tunneling operation under the dual guarantees of safety and efficiency.

[0052] In summary, the embodiments of the present application have at least the following technical effects: First, based on the formation detection and modeling data uploaded by the cloud service terminal in the first tunneling work area, a basic twin model of the formation environment is constructed. Then, a multi-source sensing device is used to identify the position and morphological characteristics of obstacles in front of the tunneling equipment. Among them, the multi-source sensing device is embedded in the tunneling equipment, and the tunneling equipment is in the first tunneling work area. Then, the position and morphological characteristics of the obstacles are input into the obstacle decoupling model library for decoupling search, and a matching obstacle twin model is output. The obstacle decoupling model library is embedded in the cloud service terminal. Further, the matching obstacle twin model is used as a plug-in and fused into the basic twin model of the formation environment in the same coordinate system to obtain a fused twin model. Finally, risk analysis of the obstacle area is carried out according to the fused twin model, a risk warning signal is output, and the risk warning signal is fed back to the tunneling equipment for risk control. This solves the technical problem of resource waste and low efficiency caused by separate modeling in underground tunneling work in the prior art, and achieves the technical effect of saving resources and improving the safety and efficiency of tunneling operations by sharing the basic twin model of the underground environment and only inserting the obstacle twin model.

[0053] Embodiment 2, based on the same inventive concept as an underground tunneling work safety warning method in the foregoing embodiment, as Figure 2 shown, the present application provides an underground tunneling work safety warning system, wherein the system includes: A model construction module 11, configured to construct a basic twin model of the formation environment based on the formation detection and modeling data uploaded by the cloud service terminal in the first tunneling work area; an identification module 12, configured to use a multi-source sensing device to identify the position and morphological characteristics of obstacles in front of the tunneling equipment, wherein the multi-source sensing device is embedded in the tunneling equipment, and the tunneling equipment is in the first tunneling work area; a search module 13, configured to input the position and morphological characteristics of the obstacles into the obstacle decoupling model library for decoupling search, and output a matching obstacle twin model, and the obstacle decoupling model library is embedded in the cloud service terminal; a fusion module 14, configured to use the matching obstacle twin model as a plug-in and fuse it into the basic twin model of the formation environment in the same coordinate system to obtain a fused twin model; an analysis module 15, configured to perform risk analysis of the obstacle area according to the fused twin model, output a risk warning signal, and feed back the risk warning signal to the tunneling equipment for risk control.

[0054] Further, the search module 13 is configured to execute the following method: Obtain underground obstacle samples from the cloud service terminal; identify the parameterized model templates corresponding to the underground obstacle samples respectively, and construct the obstacle decoupling model library; input the position and morphological characteristics of the obstacles into the obstacle decoupling model library for decoupling search with each parameterized model template, and obtain parameterized model templates with both the position similarity and the morphological similarity greater than a preset threshold.

[0055] Further, the analysis module 15 is used to execute the following method: Perform obstacle area risk analysis on the tunneling parameters of the tunneling equipment according to the fusion twin model, including collision risk, sudden change risk of resistance, risk of tunneling attitude deviation, and risk of structural deformation; calculate risks according to the collision risk, sudden change risk of resistance, risk of tunneling attitude deviation, and risk of structural deformation, and output a tunneling risk index; determine a risk level according to the tunneling risk index, and output a risk warning signal corresponding to the risk level.

[0056] Further, the analysis module 15 is used to execute the following method: Record the tunneling parameters of the tunneling equipment, where the tunneling parameters include the propulsion path, propulsion rate, and cutter head rotation speed; when the tunneling equipment receives the risk warning signal, perform gradient optimization control on the tunneling parameters to minimize the tunneling risk index, and obtain optimized tunneling parameters, where the priority of adaptive optimization control is cutter head rotation speed > propulsion rate > propulsion path; control the tunneling of the tunneling equipment according to the optimized tunneling parameters.

[0057] Further, the model construction module 11 is used to execute the following method: Detect the multiple tunneling working areas corresponding to the multiple tunneling equipment; identify N tunneling equipment in the first tunneling working area, collect N formation detection and modeling data corresponding to the N tunneling equipment, and upload the N formation detection and modeling data to the cloud service terminal to synchronously update the formation environment basic twin model.

[0058] Further, the model construction module 11 is used to execute the following method: Identify N groups of obstacle positions and morphological features corresponding to the N formation detection and modeling data; obtain N return results corresponding to the N groups of obstacle positions and morphological features in the obstacle decoupling model library, and collect M groups of obstacle positions and morphological features with empty return results, where M is a positive integer less than or equal to N; use the M groups of obstacle positions and morphological features as incremental data to update the obstacle decoupling model library.

[0059] Further, the identification module 12 is used to execute the following method: The multi-source perception device includes at least any two of an inertial navigation unit, a visual camera, an infrared / structured light depth camera, and a lidar.

[0060] Further, the search module 13 is used to execute the following method: Collect the three-dimensional point cloud data sample of the underground obstacle sample; extract the position feature sample and morphological feature sample corresponding to the three-dimensional point cloud data sample, where the morphological feature includes geometric feature and material feature; construct an obstacle parametric model template according to the position feature sample and morphological feature sample corresponding to the three-dimensional point cloud data sample.

[0061] Further, the search module 13 is used to execute the following method: Decompose each underground obstacle sample according to its structural function to obtain a plurality of obstacle components; generate an underground component obstacle model template corresponding to the underground obstacle sample according to the plurality of obstacle components. When a new underground obstacle sample is added, obtain the required obstacle components corresponding to the new underground obstacle sample; combine the required obstacle components from the underground component obstacle model template to update the obstacle decoupling model library.

[0062] It should be noted that the above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above description of specific embodiments of this specification is made. The processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0063] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0064] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A safety warning method for tunneling work, characterized in that, The method includes: Based on the formation detection and modeling data uploaded by the cloud service terminal in the first tunneling work area, constructing a basic formation environment twin model; Using multi-source sensing devices to identify the position and morphological characteristics of obstacles in front of the tunneling equipment, wherein the multi-source sensing devices are embedded in the tunneling equipment, and the tunneling equipment is in the first tunneling work area; Inputting the position and morphological characteristics of the obstacles into the obstacle decoupling model library for decoupling search, and outputting a matching obstacle twin model, and the obstacle decoupling model library is embedded in the cloud service terminal; Taking the matching obstacle twin model as a plug-in, fusing it into the basic formation environment twin model in the same coordinate system to obtain a fused twin model; Performing risk analysis on the obstacle area according to the fused twin model, outputting a risk warning signal, and feeding back the risk warning signal to the tunneling equipment for risk control.

2. The safety warning method for tunneling work according to claim 1, characterized in that, Inputting the position and morphological characteristics of the obstacles into the obstacle decoupling model library for decoupling search, the method includes: Obtaining underground obstacle samples by the cloud service terminal; Identifying the parameterized model templates corresponding to the underground obstacle samples respectively, and constructing the obstacle decoupling model library; Inputting the position and morphological characteristics of the obstacles into the obstacle decoupling model library to perform decoupling search with each parameterized model template, and obtaining a parameterized model template with both the position similarity and the morphological similarity greater than a preset threshold.

3. The safety warning method for tunneling work according to claim 1, wherein Performing risk analysis on the obstacle area according to the fused twin model, outputting a risk warning signal, the method includes: Performing risk analysis on the tunneling parameters of the tunneling equipment in the obstacle area according to the fused twin model, including collision risk, sudden change in resistance risk, tunneling attitude deviation risk, and structural deformation risk; Performing risk calculation according to the collision risk, sudden change in resistance risk, tunneling attitude deviation risk, and structural deformation risk, and outputting a tunneling risk index; Determining the risk level according to the tunneling risk index, and outputting a risk warning signal corresponding to the risk level.

4. The safety warning method for tunneling work according to claim 3, characterized in that, Feeding back the risk warning signal to the tunneling equipment for risk control, the method includes: Recording the tunneling parameters of the tunneling equipment, and the tunneling parameters include the propulsion path, propulsion rate, and cutter head rotation speed; When the tunneling equipment receives the risk warning signal, performing gradient optimization control on the tunneling parameters to minimize the tunneling risk index to obtain optimized tunneling parameters, wherein the priority of the adaptive optimization control is cutter head rotation speed > propulsion rate > propulsion path; Controlling the tunneling of the tunneling equipment according to the optimized tunneling parameters.

5. The safety warning method for tunneling work according to claim 1, characterized in that, The cloud service terminal is distributedly connected to multiple tunneling equipment, and the method further includes: Detecting multiple tunneling work areas corresponding to the multiple tunneling equipment; Identifying N tunneling equipment in the first tunneling work area, collecting N formation detection and modeling data corresponding to the N tunneling equipment, and uploading the N formation detection and modeling data to the cloud service terminal to synchronously update the basic formation environment twin model.

6. The safety warning method for tunneling work according to claim 5, characterized in that, Uploading the N formation detection and modeling data to the cloud service terminal to synchronously update the obstacle decoupling model library, the method includes: Identify the positions and morphological features of obstacles corresponding to the N sets of formation detection modeling data; Obtain N return results corresponding to the N sets of obstacle positions and morphological features in the obstacle decoupling model library, and collect M sets of obstacle positions and morphological features with empty return results, where M is a positive integer less than or equal to N; Use the M sets of obstacle positions and morphological features as incremental data to update the obstacle decoupling model library.

7. The safety warning method for tunneling work according to claim 6, characterized in that, The multi-source perception device includes at least any two of an inertial navigation unit, a visual camera, an infrared / structured light depth camera, and a lidar.

8. The safety warning method for a tunneling operation according to claim 2, characterized in that, Identify the parametric model templates corresponding to the underground obstacle samples respectively. The method includes: Collect three-dimensional point cloud data samples of the underground obstacle samples; Extract the position feature samples and morphological feature samples corresponding to the three-dimensional point cloud data samples. The morphological features include geometric features and material features; Construct an obstacle parametric model template according to the position feature samples and morphological feature samples corresponding to the three-dimensional point cloud data samples.

9. The safety warning method for tunneling work according to claim 2, characterized in that, Identify the parametric model templates corresponding to the underground obstacle samples respectively, and construct the obstacle decoupling model library. The method further includes: Decompose each underground obstacle sample according to its structure and function to obtain multiple obstacle components; Generate an underground component obstacle model template corresponding to the underground obstacle sample according to the multiple obstacle components. When a new underground obstacle sample is added, obtain the required obstacle components corresponding to the new underground obstacle sample; Combine the required obstacle components from the underground component obstacle model templates to update the obstacle decoupling model library.

10. A safety warning system for tunneling work, characterized in that, For implementing a safety warning method for a tunneling operation according to any one of claims 1-9, the system includes: A model construction module for constructing a basic twin model of the formation environment based on the formation detection modeling data of the first tunneling work area uploaded by the cloud service terminal; An identification module for using a multi-source perception device to identify the positions and morphological features of obstacles in front of the tunneling equipment, where the multi-source perception device is embedded in the tunneling equipment and the tunneling equipment is in the first tunneling work area; A search module for inputting the positions and morphological features of the obstacles into the obstacle decoupling model library for decoupling search and outputting a matching obstacle twin model. The obstacle decoupling model library is embedded in the cloud service terminal; A fusion module for using the matching obstacle twin model as a plug-in to fuse it into the basic twin model of the formation environment in the same coordinate system to obtain a fused twin model; An analysis module for performing risk analysis on the obstacle area according to the fused twin model, outputting a risk warning signal, and feeding back the risk warning signal to the tunneling equipment for risk control.

Images