A Virtual Reality Laying-out Method for Silo Cutting

Abstract

This invention discloses a virtual reality (VR) method for silo cutting, comprising: a field scanning and data acquisition stage, where multi-sensor fusion collects silo data and encrypts positioning point information; the encrypted data is transmitted via VPN and TCP protocols to a local data center and a cloud computing platform for layered storage; a 3D modeling and path calculation stage, where multi-dimensional silo data is input for modeling, and a deep learning algorithm combined with traditional mathematical methods is used to calculate the optimal cutting path, with the cloud computing platform supporting real-time path adjustment; and a cutting operation stage, where a single worker wears AR glasses to see the cutting path, and the AR glasses have functions such as positioning tracking, voice prompts, and gesture operation; and when multiple workers are cutting, workers wear AR glasses with multi-person collaboration capabilities, enabling communication and coordination, and including a task allocation module. This invention integrates multiple technologies, collects comprehensive and accurate data, provides intuitive cutting line layout, optimizes the cutting path, and offers diverse AR glasses functions, improving cutting accuracy, efficiency, and team collaboration efficiency.

Description

Technical Field

[0001] This invention relates to the field of silo cutting applications, and in particular to a virtual reality wire laying method for silo cutting. Background Technology

[0002] Silos have wide applications in industrial fields (such as grain storage and material reserves). However, with the passage of time and changes in usage requirements, silos often need to be modified, repaired, or dismantled, which involves silo cutting. Silo cutting is a complex and dangerous task, and traditional stringing methods face numerous challenges.

[0003] In common silo cutting and layout processes, the accuracy of the layout largely depends on the operator's experience. Operators determine the cutting line position based on the silo's design drawings and simple measuring tools (such as tape measures and theodolites). However, this method relies heavily on the operator's subjective judgment and the limitations of the measuring tools' precision, easily leading to layout errors. This is especially true for large or complex silos, where such errors can accumulate and affect the overall quality of the cutting work. Furthermore, since traditional layout methods are primarily based on two-dimensional drawings, operators need to mentally construct a three-dimensional silo structure and cutting path relationship. This is extremely difficult for complex silo cutting tasks, hindering accurate understanding of the cutting path and hindering effective communication with other construction personnel. This approach fails to meet the requirements of silo cutting applications. Therefore, a virtual reality layout method for silo cutting is proposed. Summary of the Invention

[0004] This invention provides a virtual reality wiring method for silo cutting, comprising the following steps:

[0005] S1 On-site Scanning and Data Acquisition Phase

[0006] S11 Multi-sensor Fusion Acquisition:

[0007] First, a comprehensive scan of the silo is conducted using laser scanning equipment, infrared sensors, and ultrasonic sensors. While collecting data, the location points are also determined through the collaborative work of these sensors. Finally, the collected data and location point information are encrypted in real time using an encryption algorithm.

[0008] S12 data transmission and storage:

[0009] The encrypted collected data and location information are transmitted to the local data center and cloud computing platform via VPN network, and stored in a specific format on the local data center and cloud computing platform for subsequent processing.

[0010] S2 3D Modeling and Path Calculation Stage

[0011] S21 AI-assisted path optimization:

[0012] The collected multi-dimensional data of the silos, including geometric shape, temperature distribution, and internal structure information, are input into 3D modeling software for modeling. The modeling software uses deep learning algorithms, which learn from a large number of existing successful silo cutting case data during the modeling process. Taking into account factors such as the wear and tear of cutting tools and the dynamic changes in cutting efficiency, the initial cutting path is calculated. Then, combined with traditional mathematical calculation methods, the initial path is optimized to obtain the optimal cutting path. Finally, the optimal cutting path is marked in a format that can be displayed by AR glasses.

[0013] Cloud computing support for S22 real-time path adjustment:

[0014] The marked optimal cutting path data and related silo model data are uploaded to the cloud computing platform. At the same time, a real-time monitoring mechanism is set up on the cloud computing platform. When an unexpected situation occurs on site, the cloud computing platform will recalculate the cutting path according to the new situation.

[0015] S3 Cutting Operation Stage

[0016] S31 single-person cutting operation:

[0017] After putting on the AR glasses, the worker turns on the cutting equipment to prepare for irregular cutting. Through the AR glasses, the worker can see the marked cutting line path. During the cutting process, as the worker's position changes, the modeling and cutting line in the AR glasses are positioned and tracked in real time using the built-in positioning and tracking system. At the same time, when the worker's operation approaches the cutting danger area and the cutting path deviates significantly, the AR glasses will issue a voice prompt to inform the worker to adjust the operation. In addition, based on the gesture recognition sensor and gesture recognition software library inside the AR glasses, the worker can zoom and rotate the cutting path displayed by the AR glasses through specific gestures, making it convenient to view the cutting path from different angles.

[0018] S32 multi-person collaborative cutting operation:

[0019] When multiple workers participate in silo cutting at the same time, each worker wears AR glasses with multi-person collaboration function. On the AR glasses, workers can see the cutting positions and paths of other workers, and can communicate and coordinate through the communication function in the glasses.

[0020] Preferably, the scanning accuracy of the laser scanning device in step S11 reaches the millimeter level to ensure that sufficiently accurate geometric data is collected, providing a reliable foundation for subsequent 3D modeling. When detecting temperature distribution, the infrared sensor has a temperature resolution of at least 0.1℃ to accurately capture subtle differences in the surface temperature of the silo. The ultrasonic sensor has a detection frequency between 20 and 100kHz.

[0021] Preferably, in step S12, the secure network transmission method is a Virtual Private Network (VPN). The VPN network establishes a private network on a public network for encrypted communication. During data transmission, the transmission control protocol (TCP) is used to ensure the reliability of data transmission and to ensure that the encrypted collected data and location information arrive at the local data center and cloud computing platform intact and without error.

[0022] Preferably, in step S12, storing data in a specific format is done according to a hierarchical storage architecture. First, the raw collected data is stored in a high-speed cache layer and a solid-state drive is used as the storage medium, which can quickly respond to data read requests and facilitate frequent access during subsequent data processing. After preliminary processing, the data is stored in a large-capacity mechanical hard drive layer to save storage costs and meet the long-term storage needs of the data. At the same time, a redundant storage strategy is adopted during the data storage process.

[0023] Preferably, the deep learning algorithm in step S21 is a deep neural network algorithm. During the algorithm training process, the stochastic gradient descent algorithm is used as the optimizer, and a momentum term is combined to accelerate convergence, so that the learning rate is set to a dynamic value. A larger learning rate is used in the early stage of training to speed up the convergence speed, and the learning rate is gradually reduced as training progresses to avoid overfitting.

[0024] Preferably, the cloud computing platform obtained in step S22 adopts a distributed computing architecture, which consists of multiple computing nodes, each of which has independent computing and storage capabilities.

[0025] Preferably, the AR glasses in step S31 have a built-in positioning and tracking system that combines a global positioning system, an inertial navigation system, and a visual positioning system. Furthermore, the speech synthesis for the voice prompts in this step uses a high-quality speech synthesis engine that can adjust the tone, speed, and volume of the speech according to different levels of danger.

[0026] Preferably, the gesture recognition sensor inside the AR glasses in step S31 is a capacitive gesture recognition sensor, which can detect minute changes in capacitance to accurately recognize the worker's gestures. The gesture recognition software library uses a machine learning-based classification algorithm. During the training phase, a large amount of sample data from different workers with different gesture habits are collected for training to improve the accuracy of gesture recognition. This allows workers to accurately zoom and rotate the cutting path displayed on the AR glasses using specific gestures, making it convenient to view the cutting path from different angles.

[0027] Preferably, the gesture recognition sensor inside the AR glasses in step S31 is a capacitive gesture recognition sensor, which can detect minute changes in capacitance to accurately recognize the worker's gestures. The gesture recognition software library uses a machine learning-based classification algorithm. During the training phase, a large amount of sample data from different workers with different gesture habits are collected for training to improve the accuracy of gesture recognition. This allows workers to accurately zoom and rotate the cutting path displayed on the AR glasses using specific gestures, making it convenient to view the cutting path from different angles.

[0028] Preferably, in step S31, the contrast and brightness of the AR glasses' display system can be adjusted, and the AR glasses' display system has multiple built-in display modes.

[0029] Preferably, the communication function between AR glasses with multi-person collaboration function in step S32 adopts 5G communication technology, and the AR glasses in this step are equipped with a task allocation module, which can allocate tasks according to each worker's skill level, experience and current work status.

[0030] In summary, compared with the prior art, the present invention provides a virtual reality wire laying method for silo cutting, which has the following beneficial effects:

[0031] 1. This invention can comprehensively and accurately acquire multi-dimensional data such as the geometry, temperature distribution, and internal structure of the silo through multi-sensor fusion, providing an accurate and reliable foundation for subsequent 3D modeling and path calculation. This helps improve the accuracy of the entire cutting operation, reduces cutting errors caused by inaccurate data, and calculates a preliminary cutting path that is more in line with the actual situation through deep learning algorithms in 3D modeling software. Then, the optimal cutting path is obtained through optimization using traditional methods, which improves the rationality and efficiency of the cutting path and reduces resource waste during the cutting process.

[0032] 2. This invention, through AR glasses and its built-in positioning and tracking system, can not only project the calculated cutting line onto the silo surface, enhancing the intuitiveness of the cutting line, but also locate and track the worker's position and the cutting line in real time, ensuring the accuracy of the cutting operation. At the same time, the multi-person collaboration function added inside the AR glasses is conducive to information sharing and communication coordination among workers, improving the efficiency of team collaboration. Attached Figure Description

[0033] Figure 1 This is a flowchart of the silo cutting and laying method of the present invention.

[0034] Figure 2 This is a flowchart of step S1 of the present invention.

[0035] Figure 3 This is a flowchart of step S2 of the present invention.

[0036] Figure 4 This is a flowchart of step S3 of the present invention. Detailed Implementation

[0037] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0038] Please see Figure 1 The present invention provides a technical solution, a virtual reality wire laying method for silo cutting, comprising the following steps;

[0039] S1 On-site Scanning and Data Acquisition Phase

[0040] Please see Figure 2 S11 multi-sensor fusion acquisition:

[0041] First, a comprehensive scan of the silo is conducted using laser scanning equipment, infrared sensors, and ultrasonic sensors. Simultaneously, positioning points are determined through the collaborative work of these sensors. Finally, the collected data and positioning point information are encrypted in real time using an encryption algorithm. The laser scanning equipment achieves millimeter-level accuracy, ensuring the acquisition of sufficiently precise geometric data to provide a reliable foundation for subsequent 3D modeling. Meanwhile, the infrared sensors, when detecting temperature distribution, have a temperature resolution of at least 0.1℃, accurately capturing subtle differences in silo surface temperature. The ultrasonic sensors operate at a frequency between 20 and 100 kHz, effectively penetrating the silo's internal structure to detect potential internal structural information, such as possible voids or uneven structures. Regarding the encryption algorithm, an advanced encryption standard algorithm with a 256-bit key length is adopted. This encryption algorithm ensures data security while also meeting the real-time requirements of the data acquisition process, guaranteeing the confidentiality of the collected data and positioning point information during transmission and storage, and preventing malicious acquisition or tampering.

[0042] S12 data transmission and storage:

[0043] The encrypted collected data and location information are transmitted to the local data center and cloud computing platform via a VPN network. The data is then stored in a specific format on the local data center and cloud computing platform for subsequent processing. The secure network transmission method is a Virtual Private Network (VPN). A VPN network establishes a private network on a public network for encrypted communication. During data transmission, the transmission control protocol is used to ensure the reliability of data transmission and ensure that the encrypted collected data and location information arrive at the local data center and cloud computing platform intact and without errors.

[0044] In step S12, storing data in a specific format is done according to a tiered storage architecture. For data storage, both in the local data center and on the cloud computing platform, the data is stored according to a tiered storage architecture. First, the raw collected data is stored in a high-speed cache layer, which uses solid-state drives as the storage medium. This layer can quickly respond to data read requests and facilitate frequent access during subsequent data processing. The data that has undergone preliminary processing is stored in a large-capacity mechanical hard drive layer to save storage costs and meet the long-term storage needs of the data. At the same time, a redundant storage strategy is adopted during the data storage process to ensure that even if a storage device fails, the integrity and availability of the data can be guaranteed through data verification and recovery mechanisms so that the subsequent processing can proceed smoothly.

[0045] S2 3D Modeling and Path Calculation Stage

[0046] Please see Figure 3 S21 AI-assisted path optimization:

[0047] The collected multi-dimensional data of the silos, including geometric shape, temperature distribution, and internal structure information, is input into 3D modeling software for modeling. This software employs a deep learning algorithm, which learns from a large amount of existing successful silo cutting case data during the modeling process. It considers factors such as tool wear and dynamic changes in cutting efficiency to calculate an initial cutting path. Then, combining traditional mathematical calculation methods, the initial path is optimized to obtain the optimal cutting path. Finally, the optimal cutting path is marked in a format suitable for AR glasses display. The deep learning algorithm is a deep neural network algorithm. When using the deep neural network algorithm to learn from a large amount of existing successful silo cutting case data, the collected multi-dimensional data is first normalized, mapping values ​​from different ranges (such as geometric dimensions, temperature values, and relevant quantitative data of the internal structure) to the same interval. This improves the convergence speed and training effect of the deep neural network algorithm. When constructing the deep neural network algorithm model, the network structure should include an input layer, multiple hidden layers, and an output layer. The number of neurons in the hidden layers is reasonably set according to the dimension and complexity of the input data. For example, for complex silo structure data, the number of neurons in the hidden layers can be set to 100- Between 500 and 100, during training, the stochastic gradient descent algorithm is used as the optimizer, combined with a momentum term to accelerate convergence. The learning rate is set to a dynamic value, with a larger learning rate used in the early stages of training to speed up convergence, and the learning rate gradually reduced as training progresses to avoid overfitting. Considering the wear and tear of the cutting tool, the model should establish a wear model based on factors such as the type of cutting tool, usage time, and hardness of the cutting material, and incorporate it into the path calculation. For the dynamic changes in cutting efficiency, the prediction model of cutting speed should be adjusted in real time according to factors such as the material of the silo and the requirements of the cutting process. Finally, the initial path is optimized by combining the traditional mathematical calculation method based on least squares to obtain the optimal cutting path and mark it in a format that can be displayed by AR glasses, such as converting it into a specific coordinate system and graphic format to ensure that AR glasses can accurately display the cutting path.

[0048] The logical framework for AI-assisted path optimization includes a data input layer, which receives multi-dimensional data collected from silos, including geometric shape, temperature distribution, and internal structure information.

[0049] The deep learning layer, based on deep learning algorithms, learns from a large amount of existing successful silo cutting case data, and calculates the initial cutting path based on the learned patterns, taking into account factors such as the wear and tear of cutting tools and the dynamic changes in cutting efficiency.

[0050] The traditional computation layer receives the initial cutting path calculated by the deep learning layer and optimizes it using traditional mathematical methods (such as geometric calculations and optimization algorithms). For example, based on the actual geometry of the silo, geometric calculations are used to adjust the cutting path to better fit the silo surface and reduce cutting errors; or optimization algorithms are used to further improve cutting efficiency and reduce cutting costs.

[0051] The output layer is used to convert the optimized cutting path into a format that can be displayed by AR glasses. This may involve converting the path data into a specific coordinate system, graphics format (such as vector graphics), etc., so that the AR glasses can accurately display the cutting path.

[0052] Cloud computing support for S22 real-time path adjustment:

[0053] The marked optimal cutting path data and related silo model data are uploaded to a cloud computing platform. A real-time monitoring mechanism is set up on the cloud computing platform. When unexpected situations occur on-site, the cloud computing platform recalculates the cutting path based on the new circumstances. The distributed computing architecture consists of multiple computing nodes, each with independent computing and storage capabilities. When the marked optimal cutting path data and related silo model data are uploaded to the cloud computing platform, the data is distributed to different computing nodes for storage and processing according to a certain load balancing strategy. Regarding the real-time monitoring mechanism, the monitored parameters include not only the physical parameters of the silo structure (such as deformation and vibration) but also other parameters. It also includes external environmental parameters (such as temperature, humidity, wind speed, etc.). When unexpected situations occur on site, such as the deformation of the silo structure exceeding the preset threshold, or the rapid change in the external temperature causing changes in the silo material properties, the cloud computing platform will recalculate the cutting path according to the new situation. During the recalculation process, the large-scale parallel computing capability of the cloud computing platform is used to call multiple computing nodes for collaborative calculation at the same time. Furthermore, when recalculating the cutting path, similar situations and coping strategies in historical cutting data will also be referenced to improve the accuracy and reliability of the new path calculation. Then, the new cutting path will be synchronized to the AR glasses in a timely manner to ensure that workers can perform cutting operations according to the new path.

[0054] S3 Cutting Operation Stage

[0055] Please see Figure 4 When operating the S31 single-person cutting system:

[0056] After putting on the AR glasses, the worker starts the cutting equipment to prepare for irregular cutting. Through the AR glasses, the worker can see the marked cutting line path. During the cutting process, as the worker's position changes, the modeling and cutting line in the AR glasses are positioned and tracked in real time using the built-in positioning and tracking system. At the same time, when the worker's operation approaches the cutting danger zone and the cutting path deviates significantly, the AR glasses will issue a voice prompt to inform the worker to adjust the operation. Based on the gesture recognition sensor and gesture recognition software library inside the AR glasses, the worker can zoom and rotate the cutting path displayed by the AR glasses using specific gestures, making it convenient to view the cutting path from different angles. The AR glasses also have a built-in positioning and tracking system that combines the Global Positioning System (GPS), the Inertial Navigation System (INS), and the Visual Positioning System (VPS). GPS is used to obtain relatively macroscopic location information to determine the approximate position of the worker in the large scene of silo cutting.

[0057] INS provides high-precision relative position information in a short time by detecting motion parameters such as acceleration and angular velocity of the AR glasses themselves. Especially when GPS signals are interfered with or cannot be obtained, it can ensure the continuity of positioning and tracking.

[0058] VPS further refines the AR glasses' position within the silo scene by recognizing visual features of the surrounding environment (such as specific markings and textures). When a worker's operation approaches a dangerous cutting area and the cutting path deviates significantly, the AR glasses' voice prompts should include specific hazard types (such as approaching uncut support structures or deviating too far from the cutting plane) and adjustment directions (such as moving left or right, or adjusting the cutting angle up or down).

[0059] Furthermore, the voice prompts utilize a high-quality voice synthesis engine, capable of adjusting the tone, speed, and volume of the voice according to different hazard levels. For example, a rapid tone and louder volume are used for high-hazard levels to ensure workers receive accurate warnings promptly. The gesture recognition sensor inside the AR glasses employs a capacitive sensor, capable of detecting minute capacitance changes to accurately identify worker gestures. The gesture recognition software library uses a machine learning-based classification algorithm. During the training phase, a large amount of sample data from different workers with varying gesture habits is collected to improve the accuracy of gesture recognition. This allows workers to accurately zoom and rotate the cutting path displayed on the AR glasses using specific gestures, facilitating viewing the cutting path from different angles.

[0060] Furthermore, the AR glasses' display system features high contrast and high brightness. High contrast ensures that the cutting path remains clearly visible even in dimly lit or complex lighting conditions inside the silo, preventing worker errors due to unclear displays. High brightness ensures that the cutting path is not obscured by strong light in bright environments (such as when sunlight shines directly into the silo). When displaying the cutting path, in addition to showing the basic cutting lines, auxiliary information is also displayed, such as the distance to the next cutting node and the current cutting progress percentage. This auxiliary information helps workers better understand the overall situation of the cutting work.

[0061] Meanwhile, the display system of AR glasses should support multiple display modes, including perspective mode, in which workers can see the real silo environment and the virtual cutting path at the same time, which facilitates operation and positioning in complex environments.

[0062] Augmented reality mode, in which the virtual cutting path is displayed in a more prominent way and can interact with certain features of the real environment (such as displaying the texture aligned with the silo surface).

[0063] S32 multi-person collaborative cutting operation:

[0064] When multiple workers participate in silo cutting at the same time, each worker wears AR glasses with multi-person collaboration function. On the AR glasses, workers can see the cutting positions and paths of other workers, and can communicate and coordinate through the communication function in the glasses. The communication function between AR glasses with multi-person collaboration function adopts 5G communication technology, and the AR glasses in this step are equipped with a task allocation module, which can allocate tasks according to each worker's skill level, experience and current work status.

[0065] This solution utilizes multi-sensor fusion to comprehensively and accurately acquire multi-dimensional data on the silo's geometry, temperature distribution, and internal structure. This provides an accurate and reliable foundation for subsequent 3D modeling and path calculation, improving the precision of the entire cutting operation and reducing cutting errors caused by inaccurate data. Furthermore, deep learning algorithms in the 3D modeling software can calculate a preliminary cutting path that better reflects the actual situation. This path is then optimized using traditional methods to obtain the optimal cutting path, improving its rationality and efficiency, and reducing resource waste during the cutting process. Additionally, AR glasses and their built-in positioning and tracking system not only project the calculated cutting line onto the silo surface, enhancing its intuitiveness, but also enable real-time positioning and tracking of the worker's position and the cutting line, ensuring the accuracy of the cutting operation. The multi-person collaboration function integrated into the AR glasses facilitates information sharing and communication among workers, improving team collaboration efficiency.

[0066] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0067] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A virtual reality wire laying method for silo cutting, characterized in that: Includes the following steps: S1 On-site Scanning and Data Acquisition Phase S11 Multi-sensor Fusion Acquisition: First, a comprehensive scan of the silo is conducted using laser scanning equipment, infrared sensors, and ultrasonic sensors. While data is being collected, the location points are also determined through the collaborative work of these sensors. Finally, the collected data and location point information are encrypted in real time using an encryption algorithm. S12 data transmission and storage: The encrypted collected data and location information are transmitted to the local data center and cloud computing platform via VPN network, and the data is stored in the local data center and cloud computing platform. S2 3D Modeling and Path Calculation Stage S21 AI-assisted path optimization: The collected multi-dimensional data of the silos, including geometric shape, temperature distribution, and internal structure information, are input into 3D modeling software for modeling. The modeling software uses a deep learning algorithm, which learns from a large number of existing successful silo cutting case data during the modeling process, and simultaneously considers factors such as the wear and tear of the cutting tools and the dynamic changes in cutting efficiency to calculate a preliminary cutting path. Then, combined with traditional mathematical calculation methods, the preliminary path is optimized to obtain the optimal cutting path. Finally, the optimal cutting path is marked in a format that can be displayed by AR glasses, specifically as follows: First, the collected multi-dimensional data is normalized to map different ranges of values, namely geometric dimensions, temperature values, and quantitative data related to the internal structure of the silo, to the same interval. When constructing the deep neural network algorithm model, the network structure is built through input layer, hidden layer, and output layer. During training, the stochastic gradient descent algorithm is used as the optimizer, combined with momentum term to accelerate convergence. A larger learning rate is used in the early stage of training to speed up the convergence speed, and the learning rate is gradually reduced as training progresses. The model then establishes a loss model based on factors such as the type of cutting tool, usage time, and hardness of the cutting material, and incorporates these factors into the path calculation. For dynamic changes in cutting efficiency, the model predicts the cutting speed in real time based on the material of the silo and the requirements of the cutting process. Finally, the model combines a mathematical calculation method based on the least squares method to optimize the initial path, obtain the optimal cutting path, and mark it in a format for display on AR glasses. Cloud computing support for S22 real-time path adjustment: The marked optimal cutting path data and related silo model data are uploaded to the cloud computing platform. At the same time, a real-time monitoring mechanism is set up on the cloud computing platform. When an unexpected situation occurs on site, the cloud computing platform will recalculate the cutting path according to the new situation. S3 Cutting Operation Stage S31 single-person cutting operation: After putting on the AR glasses, the worker turns on the cutting equipment to prepare for irregular cutting. Through the AR glasses, the worker can see the marked cutting line path. During the cutting process, as the worker's position changes, the modeling and cutting line in the AR glasses are located and tracked in real time using the built-in positioning and tracking system. At the same time, when the worker's operation approaches the cutting danger area and the cutting path deviates significantly, the AR glasses issue a voice prompt to inform the worker to adjust the operation. In addition, based on the gesture recognition sensor and gesture recognition software library inside the AR glasses, the worker can zoom and rotate the cutting path displayed by the AR glasses through specific gestures, making it convenient to view the cutting path from different angles. S32 multi-person collaborative cutting operation: When multiple workers participate in silo cutting at the same time, each worker wears AR glasses with multi-person collaboration function. On the AR glasses, workers can see the cutting positions and paths of other workers, and can communicate and coordinate through the communication function in the glasses.

2. The virtual reality wire laying method for silo cutting according to claim 1, characterized in that: The laser scanning device in step S11 should have a scanning accuracy of millimeters to ensure that sufficiently accurate geometric data is collected, providing a reliable foundation for subsequent 3D modeling. The infrared sensor should have a temperature resolution of at least 0.1℃ when detecting temperature distribution to accurately capture subtle differences in the surface temperature of the silo. The ultrasonic sensor should have a detection frequency between 20 and 100kHz.

3. The virtual reality wire laying method for silo cutting according to claim 1, characterized in that: In step S12, the secure network transmission method is a Virtual Private Network (VPN). The VPN network establishes a private network on a public network for encrypted communication. During data transmission, the transmission control protocol (TCP) is used to ensure the reliability of data transmission and to ensure that the encrypted collected data and location information arrive at the local data center and cloud computing platform intact and without error.

4. The virtual reality wire laying method for silo cutting according to claim 1, characterized in that: The data storage in step S12 is carried out according to a hierarchical storage architecture. First, the raw collected data is stored in the high-speed cache layer and solid-state drives are used as the storage medium, which can quickly respond to data read requests and facilitate frequent access in the subsequent data processing process. After preliminary processing, the data is stored in the large-capacity mechanical hard drive layer to save storage costs and meet the long-term storage needs of the data. At the same time, a redundant storage strategy is adopted in the data storage process.

5. The virtual reality wire laying method for silo cutting according to claim 1, characterized in that: In step S22, it is found that the cloud computing platform adopts a distributed computing architecture, which consists of multiple computing nodes, each of which has independent computing and storage capabilities.

6. The virtual reality wire laying method for silo cutting according to claim 1, characterized in that: The AR glasses in step S31 have a built-in positioning and tracking system that combines a global positioning system, an inertial navigation system, and a visual positioning system. In addition, the speech synthesis for the voice prompts in this step uses a high-quality speech synthesis engine that can adjust the tone, speed, and volume of the speech according to different levels of danger.

7. The virtual reality wire laying method for silo cutting according to claim 1, characterized in that: In step S31, the gesture recognition sensor inside the AR glasses is a capacitive gesture recognition sensor, which can detect minute changes in capacitance to accurately recognize the worker's gestures. The gesture recognition software library uses a machine learning-based classification algorithm. During the training phase, it collects a large amount of sample data from different workers with different gesture habits to improve the accuracy of gesture recognition. This allows workers to accurately zoom and rotate the cutting path displayed on the AR glasses using specific gestures, making it convenient to view the cutting path from different angles.

8. The virtual reality wire laying method for silo cutting according to claim 1, characterized in that: In step S31, the AR glasses' display system has the characteristics of high contrast and high brightness, and the AR glasses' display system also has multiple built-in display modes.

9. The virtual reality wire laying method for silo cutting according to claim 1, characterized in that: In step S32, the communication function between AR glasses with multi-person collaboration function adopts 5G communication technology, and the AR glasses in this step are equipped with a task allocation module, which can allocate tasks according to each worker's skill level, experience and current work status.

Images