Underground rock mass intelligent surveying system based on high-density resistivity and surveying method of underground rock mass intelligent surveying system

Abstract

The invention relates to an underground rock mass intelligent surveying system based on high-density resistivity, and aims to provide a high-precision surveying solution capable of automatically identifying and analyzing underground substance distribution. The system is composed of a data acquisition module, an intelligent data processing and analysis module, a three-dimensional visualization module, a user interaction interface, a data sharing and cloud service module, an automatic survey path planning module and a safety and reliability guarantee module. Innovation points comprise an adaptive data acquisition algorithm, a multi-source data fusion technology, an intelligent diagnosis and prediction model, a low-energy-consumption long-acting operation design and a modular hardware architecture. The system can monitor underground environment change in real time, generate a visual three-dimensional geologic model, and support data sharing and remote access through the cloud platform. According to the surveying method, surveying precision and efficiency are improved, cost is reduced, and the surveying method is suitable for multiple fields of urban construction, geological research, environment monitoring and the like.

Description

Technical Field

[0001] The present invention belongs to the field of geological survey technology, and in particular refers to an underground rock survey system that combines modern sensing technology, data processing algorithms, artificial intelligence, three-dimensional visualization technology and cloud services. Background Art

[0002] In the field of geological survey, the structure and properties of underground rock mass are of great significance for resource development, urban planning and environmental assessment. Traditional underground survey methods mainly rely on manually operated geological drilling and resistivity measurement, which have disadvantages such as low efficiency, limited data accuracy and inability to update survey results in real time. With the advancement of science and technology, although some automated survey equipment has emerged, they often lack intelligent processing capabilities, are difficult to adapt to the changing underground environmental conditions, and are difficult to achieve accurate analysis of complex underground structures.

[0003] Existing technologies are often independent of each other in data collection, processing and analysis, and lack an effective data fusion mechanism, which limits the accuracy and application scope of survey results. The visualization of survey data also mostly remains at the two-dimensional level, making it difficult to intuitively display complex three-dimensional underground structures. In terms of data sharing and remote collaboration, existing systems have also failed to fully utilize cloud computing and big data technologies, which to some extent affects the collaborative efficiency of survey work and the real-time nature of data.

[0004] In view of the above problems, the present invention proposes an intelligent underground rock mass survey system based on high-density resistivity. The system integrates advanced sensors, intelligent data processing algorithms, three-dimensional visualization technology and cloud service platform to achieve automation, intelligence and efficiency of underground rock mass survey. Through this system, the accuracy and efficiency of survey can be significantly improved, the survey cost can be reduced, and the survey data can be updated and shared in real time, providing more accurate and reliable underground structure information for geological research and engineering applications. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent underground rock survey system and a survey method based on high-density resistivity, which can realize high-precision, automated and intelligent survey of underground rock masses, improve survey efficiency, reduce costs, and provide real-time and accurate underground structure information.

[0006] The intelligent underground rock survey system realizes efficient and automated underground survey processes through a series of precisely integrated modules. The core of the system is started by a data acquisition module composed of multiple resistivity sensors, which capture the resistivity data of the underground rock mass in real time. Subsequently, the signal processing unit filters, amplifies and digitizes the original signal to ensure the accuracy and availability of the data. The data processing and analysis module is equipped with an adaptive algorithm to deeply analyze the processed data, while the intelligent diagnosis and prediction module uses machine learning technology to intelligently identify and trend the underground structure. The analysis results are converted into a three-dimensional geological model that users can intuitively understand through the three-dimensional visualization module, and displayed on the user interface, allowing users to monitor and operate in real time. The data sharing and cloud service module ensures the safe storage of processed data and supports remote access, realizing instant data sharing and team collaboration. The automated survey path planning module dynamically adjusts the survey strategy according to survey needs and environmental feedback, and guides the data acquisition module to efficiently complete the survey task. The power management module provides stable and lasting energy support for the system, while the safety and reliability assurance module ensures the stable operation of the system in various environments through multiple protection measures, forming a comprehensive, coherent and automated survey solution.

[0007] In addition to multiple resistivity sensors, the data acquisition module also integrates a global positioning system (GPS) unit for synchronous acquisition of time stamps and geographic location information. This GPS unit can provide time synchronization signals with nanosecond accuracy, ensuring the consistency and accuracy of data across sensors. At the same time, the integration of the GPS unit enables each set of resistivity data to be associated with specific geographic coordinates, providing an accurate spatial reference for survey data. During the data acquisition process, the GPS unit receives and records satellite signals in real time, calculates the longitude, latitude and altitude of the survey point, and embeds this information into the data stream in a standard format. In this way, when the signal processing unit receives the data from the resistivity sensor, it can also obtain the corresponding timestamp and geographic tag at the same time, so that in the data processing and analysis stage, the structure of the underground rock mass can be more accurately spatially located and analyzed. The realization of this function enhances the system's ability to manage and interpret survey data, provides key spatial and temporal information for subsequent automated survey path planning and three-dimensional visualization, and ensures the reliability and practicality of the survey results.

[0008] In the system as claimed in claim 1 or 2, the signal processing unit further refines its function, in particular, it includes an analog-to-digital converter (ADC) for converting the continuous analog signals collected by the resistivity sensor and the GPS unit into discrete digital signals for subsequent digital signal processing. The ADC has a resolution of at least 24 bits and a sampling rate of up to 100 megasamples per second (MSPS), ensuring high fidelity and high speed of the signal digitization process. In specific operation, the ADC receives analog resistivity signals from the data acquisition module, and converts these signals into corresponding digital values ​​through its high-precision converter, which are then used for further analysis and processing of the system. The high resolution of the analog-to-digital conversion process ensures that even small changes in the signal can be accurately captured by the system, while the high sampling rate ensures the continuity of the rapidly changing signal without losing information due to conversion. Through this design, the signal processing unit not only improves the quality and availability of the data, but also lays a solid foundation for the real-time response and high-precision data analysis of the system.

[0009] The advanced nature of the data processing and analysis module is reflected in its integrated dedicated data fusion algorithms, which are designed to efficiently integrate data streams from multiple sensors in the system. Specifically, the module uses synchronous data fusion technology to merge and calibrate data from resistivity sensors and GPS units in real time in microseconds. The algorithm combines advanced filtering technologies such as Kalman filters and particle filters to align multi-source data in space and time with an accuracy of at least 95%, eliminate data redundancy, and enhance the consistency and reliability of information. The data processing and analysis module also has an intelligent weight allocation mechanism to dynamically adjust the weight of each sensor data in the fusion result according to its quality and importance to ensure the optimal performance of the final data set. In addition, the module also implements adaptive filtering function, which can automatically adjust the filtering parameters according to the characteristics of the underground rock mass and the changes in the survey environment to adapt to different geological conditions and survey needs. Through this comprehensive data fusion processing, the system can provide a more accurate and comprehensive view of the underground structure, provide high-quality input data for the intelligent diagnosis and prediction module, and thus improve the analysis ability and prediction accuracy of the entire survey system.

[0010] The core of the intelligent diagnosis and prediction module is its integrated deep learning network, which is specially designed for pattern recognition. The deep learning network adopts the convolutional neural network (CNN) architecture and has a deep structure of at least 5 layers, including convolutional layers, pooling layers and fully connected layers, to achieve automatic extraction of underground rock structure features and recognition of complex patterns. The network training uses at least 100,000 labeled images of geological structures, and trains the model with a classification accuracy of at least 95% through the back propagation algorithm and Adam optimizer, ensuring high-accuracy identification of underground rock types. The module also includes a recurrent neural network (RNN), especially a long short-term memory network (LSTM), which is used to process time series data and predict the long-term evolution trend of underground rock structure. The LSTM network can memorize information up to 1,000 time steps and predict future changes with an accuracy of at least 90%. In addition, the input layer of the deep learning network is designed with an adaptive feature selection mechanism, which can dynamically adjust the input features of the network according to the importance of the current survey data and optimize the network performance.

[0011] The training and reasoning processes of the intelligent diagnosis and prediction module are all carried out in a GPU accelerated environment, ensuring processing speed and real-time performance. The module also includes an online learning component that allows the system to continuously learn from new data during the survey process and automatically update the parameters of the deep learning model to adapt to the dynamic changes in the geological environment. This integrated deep learning network significantly improves the system's intelligent diagnosis capabilities and prediction accuracy, providing strong technical support for underground rock surveys.

[0012] The 3D visualization module further enhances its functionality by including a dedicated graphics processing unit (GPU) for efficient rendering of complex geological models. The GPU has at least 2048 core processors and 4GB of GDDR5 video memory, capable of rendering high-resolution 3D geological structure models at a rate of 60 frames per second. The module uses advanced graphics rendering technologies such as ray tracing and high-level shading language to provide realistic visual effects, while supporting multiple light sources, shadows and reflection effects, enhancing the three-dimensionality and realism of the model. The 3D visualization module also includes a user-interactive interface that allows users to explore geological models from different angles and levels through operations such as rotation, scaling and slicing. The interface supports real-time rendering feedback with a response time of less than 10 milliseconds, ensuring smooth and intuitive user operations. In addition, the module also integrates data encoding and decoding algorithms that can quickly process and parse geological data from the data processing and analysis module and convert it into vertex and texture information required for the 3D model.

[0013] Furthermore, the 3D visualization module also uses multi-threading and asynchronous computing technology to optimize the allocation and use of GPU resources. The module supports output with at least 4K resolution, provides a high-definition visual experience, and can intelligently adjust rendering parameters such as transparency and color mapping according to different geological features to highlight specific geological structures or abnormal areas. This integrated GPU significantly improves the performance of the 3D visualization module and provides intuitive, real-time and high-quality visualization results for intelligent exploration of underground rock masses.

[0014] The user interface is designed with intuitiveness and ease of use in mind. It includes a high-resolution touch screen and a set of carefully laid out physical buttons. The touch screen has multi-touch capabilities, can accurately identify up to 10 simultaneous touches, and supports gestures such as zooming, rotating, and dragging, ensuring that users can interact with the 3D geological model intuitively and smoothly. The physical buttons provide shortcuts, including but not limited to model view switching, layer control, measurement tools, and preset functions. These buttons have clear labels and tactile feedback, which facilitates users to operate blindly without watching the screen. The user interface also integrates an advanced menu system, which is accessed through the touch screen or physical buttons, providing detailed setting options such as rendering quality adjustment, user preference configuration, and help documentation. The interface design takes into account the needs of different users and supports custom shortcut keys and interface layouts to adapt to the usage habits of different users. The combination of physical buttons and touch screens provides users with flexible operation methods, whether it is a field survey that requires fast response or a sophisticated office analysis, it can provide an efficient user experience. This comprehensive user interface design significantly improves the accessibility and user satisfaction of the system.

[0015] The data sharing and cloud service module further enhances its functionality, including a dedicated server for data synchronization and version control. The server has a storage capacity of at least 1TB and a data processing capacity of at least 10Gbps, ensuring the storage and rapid processing of large amounts of geological data. The server adopts a distributed architecture and supports data access and operations by at least 1,000 concurrent users, ensuring data consistency and availability in a high-concurrency environment. The server integrates advanced data synchronization technology and can synchronize changes to all connected clients within 5 seconds after the data is updated, ensuring that all users have access to the latest data. The version control function allows users to track and roll back data historically, supports the storage and management of at least 1,000 versions of data, and facilitates users to compare and analyze data states at different time points.

[0016] Furthermore, the server also provides a data backup and recovery mechanism, automatically backing up data every day, and being able to complete data recovery within 30 minutes when data is lost or damaged, ensuring data security. The server also supports fine-grained access control and permission management, allowing system administrators to assign different data access rights based on user roles and needs, ensuring data security and compliance. The server also has an API interface that allows third-party applications and services to be integrated with the cloud platform, expanding the compatibility and functionality of the system. Through this integrated server, the data sharing and cloud service module provides users with a secure, reliable and feature-rich data sharing and management platform, significantly improving the collaboration efficiency and data processing capabilities of the entire survey system.

[0017] The automated survey path planning module further integrates advanced laser radar (LiDAR) sensors for real-time environmental perception and obstacle avoidance. The LiDAR sensor has 360-degree full coverage, can measure at a rate of up to 1 million points per second, provides a spatial resolution of 0.05 meters and a detection distance of up to 500 meters, ensuring accurate planning and dynamic adjustment of the survey path. The data of the LiDAR sensor is combined with the geographic information of the GPS unit to achieve three-dimensional spatial modeling of the survey area and provide accurate environmental information for automated path planning. The sensor data is processed by a real-time obstacle detection algorithm, which can identify at least 80% of obstacle types and complete obstacle detection and classification within 100 milliseconds. The automated survey path planning module uses this data and uses a graph search-based path optimization algorithm, such as the A* algorithm or the Dijkstra algorithm, to calculate the optimal survey path and update it in real time to avoid dynamically appearing obstacles. The module also integrates a machine learning algorithm to automatically optimize the path planning strategy by learning the historical data of the survey task, thereby improving the efficiency and accuracy of path planning.

[0018] Furthermore, the module also has an interface with the intelligent diagnosis and prediction module to receive underground structure prediction information and incorporate the prediction results into path planning considerations to achieve more comprehensive survey coverage. The automated survey path planning module significantly improves the system's adaptability to complex environments through this integrated LiDAR sensor and intelligent algorithm, ensuring efficient and safe execution of survey tasks.

[0019] The detailed steps of the survey method of the underground rock mass intelligent survey system based on high-density resistivity are as follows:

[0020] S1. Initialize the survey task: configure system parameters, including the sensitivity of the resistivity sensor, the positioning accuracy of the GPS unit, the filtering parameters of the signal processing unit, etc., to ensure that the system is initialized according to the survey requirements.

[0021] S2. Deploy data acquisition module: deploy at least 32 resistivity sensors in the survey area according to the predetermined grid layout to realize multi-point synchronous high-density resistivity data acquisition, and the acquisition frequency is set to at least once per second.

[0022] S3. Signal processing: Use the signal processing unit to filter the collected analog signal, set the filter frequency range to 0.1Hz to 1kHz to remove noise; and perform digital conversion, using at least 24-bit ADC to ensure the accuracy of signal digitization.

[0023] S4. Data processing and analysis: Through the data processing and analysis module, data fusion algorithms are applied to integrate different sensor data to achieve at least 95% accuracy and conduct real-time data analysis.

[0024] S5. Intelligent diagnosis and prediction: Using the intelligent diagnosis and prediction module and a deep learning network, the underground rock structure is intelligently identified, achieving a classification accuracy of over 95% and predicting the trend of rock changes.

[0025] S6. 3D visualization: The output results of the data processing and analysis module are converted into a 3D geological model through the 3D visualization module and rendered at a rate of 30 frames per second to ensure the dynamic display effect of the model.

[0026] S7. User interaction: The 3D geological model is displayed through the user interaction interface, and the user's input and operation instructions are received. The interface response time is less than 10 milliseconds to ensure the real-time nature of user operations.

[0027] S8. Data Sharing and Cloud Services: Use the data sharing and cloud services module to synchronize and store survey data through the cloud platform, support a data transmission rate of at least 1Gbps, and realize remote access to data and team collaboration.

[0028] S9. Automated survey path planning: Based on the planning results of the automated survey path planning module, the LiDAR sensor is used for environmental perception, the survey path is dynamically adjusted, and the movement of the survey equipment is guided.

[0029] S10. Power management: Monitor the power management module to ensure that the survey system can run stably for at least 24 hours in the field environment and optimize battery usage through an efficient energy management system.

[0030] S11. Safety and reliability assurance: Use the safety and reliability assurance module to monitor the system operation status, realize fault self-diagnosis and automatic recovery, and ensure the stable operation of the system in complex environments.

[0031] S12. Result analysis and report generation: Analyze the survey results and generate a survey report containing geological models, diagnostic results and predicted trends to provide a scientific basis for subsequent decision-making.

[0032] Through this series of steps, the survey method realizes the automated and intelligent survey of underground rock masses, and provides accurate and comprehensive data support and decision-making basis.

[0033] The technical solution of the present invention can bring the following significant technical effects:

[0034] 1. Improve survey accuracy and efficiency: The system of the present invention realizes multi-point synchronous data acquisition through a high-density resistivity sensor array. Combined with an adaptive data acquisition algorithm, it can automatically adjust measurement parameters for different geological conditions, significantly improving the accuracy of data acquisition. At the same time, the system's built-in intelligent diagnosis and prediction model uses machine learning algorithms to quickly analyze the collected data, which greatly reduces data processing time and improves the efficiency of survey work compared to traditional methods.

[0035] 2. Enhance the real-time and dynamic monitoring capabilities of data: The system has real-time data processing and analysis capabilities, which can instantly reflect the slight changes in the underground rock mass and provide users with dynamic monitoring results. Combined with the automated survey path planning module, the system can automatically adjust the survey path according to real-time monitoring data, optimize the survey strategy, ensure the continuity and comprehensiveness of the survey work, and provide geological engineers with continuously updated underground environmental information.

[0036] 3. Realize 3D visualization and data sharing: The 3D visualization module of the present invention can intuitively display the complex underground rock structure in the form of a 3D model, allowing users to understand and analyze the underground situation from different angles and levels. In addition, the data sharing and cloud service module supports remote access and multi-user collaboration of survey data, and realizes secure storage, encrypted transmission and real-time synchronization of data through the cloud platform, which improves the accessibility of data and the efficiency of team collaboration, and also facilitates the long-term preservation of data and historical comparative analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The patented underground rock mass intelligent survey system

[0038] Figure 2 Flow chart of the survey method of the patented underground rock mass intelligent survey system DETAILED DESCRIPTION

[0039] The following will be combined with the attached embodiment of the present invention Figure 1 and Figure 2, the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] The purpose of the present invention is to provide an intelligent underground rock survey system and a survey method based on high-density resistivity, which can realize high-precision, automated and intelligent survey of underground rock masses, improve survey efficiency, reduce costs, and provide real-time and accurate underground structure information.

[0041] The underground rock mass intelligent survey system of the present invention adopts a data acquisition module composed of at least 32 high-precision resistivity sensors, which are evenly distributed at a spacing of 0.5 meters to capture underground resistivity data of 0.01 to 100 ohm meters in real time. The signal processing unit filters the collected analog signal from 0.1Hz to 1kHz, and amplifies the gain up to 120dB, and then digitizes it through a 24-bit analog-to-digital converter. The data processing and analysis module applies an adaptive algorithm to analyze the data with an accuracy of at least 99%, and the intelligent diagnosis and prediction module uses deep learning technology to achieve an accuracy rate of more than 95% in underground structure recognition. The three-dimensional visualization module converts the analysis results into a three-dimensional geological model at a refresh rate of 30 frames per second, and the user interaction interface provides real-time feedback at a response speed of 10 milliseconds, supporting multi-touch and physical button operations. The data sharing and cloud service module ensures data security through AES256-bit encryption technology, supports a data transmission rate of at least 1Gbps, and realizes instant data sharing across regions. The automatic survey path planning module can dynamically adjust the path within 5 seconds according to the survey task and environmental feedback. The power management module uses a high-energy lithium polymer battery to provide at least 24 hours of continuous working capacity. The safety and reliability guarantee module includes IP68-level waterproof and dustproof design, as well as anti-electromagnetic interference capability, to ensure that the system can operate stably in an environment of -40℃ to 85℃, forming a comprehensive, coherent and automated survey solution.

[0042] The data acquisition module further integrates a high-precision global positioning system (GPS) unit, which can collect and mark the precise time and geographic location of each set of resistivity data in real time with a time synchronization accuracy better than 10 nanoseconds and a spatial positioning accuracy better than 3 meters. Specifically, the GPS unit calculates the longitude, latitude and altitude of the survey point in the WGS-84 coordinate system by receiving signals from at least 4 satellites, and records this information synchronously with the resistivity data with a timestamp accuracy of microseconds. During this process, the resistivity sensor of the data acquisition module collects data at a sampling frequency of at least once per second, while the GPS unit provides time stamps and geographic coordinate information at an update frequency of at least once per second, ensuring that each record in the data stream has a clear timestamp and spatial reference. This integrated design not only improves the accuracy and reliability of data acquisition, but also provides a precise time and space reference for data processing and analysis, 3D visualization, and automated survey path planning, making the entire survey process more efficient, accurate, and intelligent.

[0043] The signal processing unit contains a high-performance analog-to-digital converter (ADC) with a resolution of at least 24 bits, ensuring that the accuracy of signal conversion reaches \(2^{24}\) discrete levels, and a sampling rate of up to 100 megasamples per second (MSPS), enabling the system to capture signal changes with a maximum frequency of 50MHz. Specifically, after the data acquisition module collects the analog resistivity signal, the ADC converts these continuous signals into digital form at a rate of at least 1 billion times per second, achieving high-fidelity signal digitization. During the conversion process, the ADC's quantization error is less than 0.5%, the signal-to-noise ratio (SNR) is higher than 90dB, and the total harmonic distortion plus noise (THD+N) is less than -100dB. These parameter indicators ensure the quality and accuracy of the digitized signal. Through this high-precision and high-speed analog-to-digital conversion, the signal processing unit provides a solid foundation for subsequent data processing and analysis, enabling the system to achieve accurate measurement and rapid response to changes in underground rock resistivity.

[0044] The data processing and analysis module achieves efficient integration of data from different sensors through an integrated data fusion algorithm. The algorithm uses an advanced Kalman filter with a 0.1 second time update cycle and a 1Hz data processing rate to ensure the real-time and accuracy of data fusion. The intelligent weight distribution mechanism in the module is dynamically adjusted according to the signal-to-noise ratio of each sensor data, where the dynamic range of the signal-to-noise ratio is 20dB to 60dB, and the response time of weight adjustment is less than 0.01 seconds, ensuring the optimality of the data fusion results. The adaptive filtering function automatically adjusts the filtering parameters according to the resistivity changes of the underground rock mass, adapting to the changes in geological conditions with a frequency range from 1mHz to 10Hz, ensuring that at least 90% of the data fusion accuracy can be obtained under different geological environments. In addition, the data fusion algorithm also includes a feedback correction mechanism with a correction accuracy of 0.05%, which can optimize the fusion effect in real time during the data acquisition process, and ultimately provide accurate, comprehensive and high-quality input data for the intelligent diagnosis and prediction module, significantly improving the reliability of the survey results and the overall performance of the system.

[0045] The intelligent diagnosis and prediction module further integrates a deep learning network for pattern recognition, which consists of a convolutional neural network (CNN) with at least 5 layers of depth, including 32 convolution filters, each with a 3x3 convolution kernel, and a 2x2 maximum pooling layer, with nonlinear transformation through the ReLU activation function. CNN training uses a dataset containing more than 100,000 geological structure images, and uses the Adam optimizer and cross entropy loss function to achieve an image classification accuracy of more than 95%. The module also contains a long short-term memory network (LSTM) with 128 memory units, which can process sequence data with a time step of 100 and predict the evolution trend of underground rock mass structure with a prediction accuracy of more than 90%. The input layer of the deep learning network adopts an adaptive feature selection mechanism to dynamically adjust the feature weights according to the relevance of the data to optimize the network performance.

[0046] The deep learning network training and reasoning process of the intelligent diagnosis and prediction module is carried out in an accelerated environment with a high-performance GPU. The GPU has at least 4GB of video memory, ensuring at least one trillion floating-point operations per second, guaranteeing the real-time processing needs of the module. The online learning component allows the system to learn from new data during the survey and automatically update the parameters of the deep learning model with an update cycle of 1 minute to adapt to the dynamic changes in the geological environment. This deeply integrated intelligent diagnosis and prediction module significantly improves the system's intelligent identification and prediction capabilities for underground rock structures, providing strong technical support for underground surveys.

[0047] In the system as claimed in any one of claims 1 to 5, the three-dimensional visualization module realizes efficient rendering of the geological model by integrating a high-performance graphics processing unit (GPU). The GPU has at least 2048 core processors and is equipped with 4GB GDDR5 high-speed video memory, and can render complex three-dimensional geological structure models at a high refresh rate of 60 frames per second. The rendering technology used by the module includes a ray tracing algorithm that supports real-time global illumination and a physically based rendering (PBR) technology to ensure that the model can present realistic effects under different lighting conditions.

[0048] The user interface allows users to perform rotation, zooming, and explore different levels of the geological model through slice views. The response time of all interactive operations does not exceed 10 milliseconds, ensuring the immediacy and smoothness of user operations. In addition, the built-in data parsing engine of the 3D visualization module can convert the geological data output by the data processing and analysis module into vertex and texture information of the 3D model within 500 milliseconds. In order to improve rendering performance, the module adopts multi-threaded rendering technology, optimizes the parallel processing capability of GPU resources, and supports high-definition output with at least 4K resolution. The intelligent rendering parameter adjustment function can automatically adjust parameters such as transparency and color mapping according to the different characteristics of the geological model to enhance the visualization of specific geological structures. For example, for key geological features such as faults or veins, the module can automatically enhance their visibility in the 3D view. This integrated GPU significantly improves the rendering quality and efficiency of the 3D visualization module, providing users with a clear, dynamic and interactive underground rock visualization experience. The user interface provides efficient user input by integrating a 10-point touch capacitive touch screen and 12 backlit physical buttons. The touch screen supports a full HD resolution of at least 1920×1080 pixels to ensure clear and delicate images, and has a fast response time of less than 5 milliseconds, allowing users to perform precise gestures such as zooming, rotating and dragging. The physical buttons are designed to have a tactile response with feedback within 0.5 seconds, providing one-click access to commonly used functions such as model view switching, layer control and measurement tools. The interface also includes a customizable advanced menu system with a menu depth of no more than three layers, ensuring that users can access all functions within three clicks. The system supports localized interfaces in at least 5 languages ​​to meet the language needs of different users. In addition, both the touch screen and physical buttons are designed with night mode, and the screen brightness can be adjusted to a minimum of 1 nit suitable for night operation to reduce the impact on user vision.

[0049] The user interface also integrates a customization function, allowing users to adjust shortcut keys and interface layouts according to personal preferences and store at least 10 different user profiles. Both the physical buttons and the touch screen have passed at least 1 million durability tests to ensure long-term reliability. This comprehensively designed user interface provides users with a flexible, intuitive and responsive operating experience, providing efficient user interaction whether it is a fast-response field survey or a sophisticated office analysis.

[0050] In the system according to any one of claims 1 to 7, the data sharing and cloud service module includes a high-performance server with at least 1TB of enterprise-level solid-state drive (SSD) storage capacity and a network throughput of up to 10Gbps, ensuring rapid storage and retrieval of geological data. The server achieves data synchronization in seconds, can push changes to all online clients within 5 seconds after data is updated, and supports at least 1,000 concurrent users to access and edit data in real time.

[0051] In terms of version control, the server can manage at least 1,000 data versions, and the differences between each version are recorded as atomic operations. Users can perform historical version backtracking and comparative analysis. Data security is guaranteed by a daily automatic backup mechanism, and the backup data is stored in an encrypted remote location. The server can complete data recovery within 30 minutes in the event of any data loss or damage.

[0052] Strict access control: The server provides customized data access rights for users at different levels through the role-based access control system (RBAC) to ensure data security and compliance. In addition, the server also provides a RESTful API interface that supports JSON and XML data formats, allowing third-party applications to seamlessly integrate with cloud service modules to achieve extended functions of data and services.

[0053] The server's monitoring system can track data access and operation behaviors in real time, generate detailed access logs and reports, and help system administrators conduct audits and monitoring. This integrated server provides an efficient, secure, and reliable data synchronization and version control center for data sharing and cloud service modules, significantly improving the system's data management and collaboration capabilities.

[0054] The automated survey path planning module achieves environmental perception by integrating a high-precision laser radar (LiDAR) sensor, which provides 360-degree full coverage and measures at a rate of 1 million points per second, ensuring a spatial resolution of 0.05 meters and a detection distance of up to 500 meters. The LiDAR sensor works in conjunction with the GPS unit to achieve accurate three-dimensional spatial modeling of the survey area, where the LiDAR data is processed by a real-time obstacle detection algorithm, which can identify and classify at least 80% of obstacle types within 100 milliseconds. The module uses path optimization technology based on the A* algorithm, combined with LiDAR sensor data and machine learning algorithms, to automatically learn and optimize the survey path planning strategy, improving the efficiency and accuracy of path planning. In addition, the module also considers the underground structure prediction information provided by the intelligent diagnosis and prediction module, and incorporates this information into the path planning to achieve comprehensive coverage and optimization of the survey task. The automated survey path planning module can pre-plan the path before the survey, and dynamically adjust the path according to the real-time feedback of the LiDAR sensor during the survey to avoid new obstacles or adapt to environmental changes, ensuring that the survey equipment completes the task safely and efficiently. This integrated LiDAR sensor and intelligent algorithm significantly improves the system's adaptability to complex environments and the efficiency of survey tasks.

[0055] The detailed steps of the survey method of the underground rock mass intelligent survey system based on high-density resistivity are as follows:

[0056] S1. Initialize the survey task: configure system parameters, including the sensitivity of the resistivity sensor, the positioning accuracy of the GPS unit, the filtering parameters of the signal processing unit, etc., to ensure that the system is initialized according to the survey requirements.

[0057] S2. Deploy data acquisition module: deploy at least 32 resistivity sensors in the survey area according to the predetermined grid layout to realize multi-point synchronous high-density resistivity data acquisition, and the acquisition frequency is set to at least once per second.

[0058] S3. Signal processing: Use the signal processing unit to filter the collected analog signal, set the filter frequency range to 0.1Hz to 1kHz to remove noise; and perform digital conversion, using at least 24-bit ADC to ensure the accuracy of signal digitization.

[0059] S4. Data processing and analysis: Through the data processing and analysis module, data fusion algorithms are applied to integrate different sensor data to achieve at least 95% accuracy and conduct real-time data analysis.

[0060] S5. Intelligent diagnosis and prediction: Using the intelligent diagnosis and prediction module and a deep learning network, the underground rock structure is intelligently identified, achieving a classification accuracy of over 95% and predicting the trend of rock changes.

[0061] S6. 3D visualization: The output results of the data processing and analysis module are converted into a 3D geological model through the 3D visualization module and rendered at a rate of 30 frames per second to ensure the dynamic display effect of the model.

[0062] S7. User interaction: The 3D geological model is displayed through the user interaction interface, and the user's input and operation instructions are received. The interface response time is less than 10 milliseconds to ensure the real-time nature of user operations.

[0063] S8. Data Sharing and Cloud Services: Use the data sharing and cloud services module to synchronize and store survey data through the cloud platform, support a data transmission rate of at least 1Gbps, and realize remote access to data and team collaboration.

[0064] S9. Automated survey path planning: Based on the planning results of the automated survey path planning module, the LiDAR sensor is used for environmental perception, the survey path is dynamically adjusted, and the movement of the survey equipment is guided.

[0065] S10. Power management: Monitor the power management module to ensure that the survey system can run stably for at least 24 hours in the field environment and optimize battery usage through an efficient energy management system.

[0066] S11. Safety and reliability assurance: Use the safety and reliability assurance module to monitor the system operation status, realize fault self-diagnosis and automatic recovery, and ensure the stable operation of the system in complex environments.

[0067] S12. Result analysis and report generation: Analyze the survey results and generate a survey report containing geological models, diagnostic results and predicted trends to provide a scientific basis for subsequent decision-making.

[0068] Through this series of steps, the survey method realizes the automated and intelligent survey of underground rock masses, and provides accurate and comprehensive data support and decision-making basis.

[0069] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An intelligent underground rock mass survey system based on high-density resistivity, characterized in that: include: The data acquisition module, signal processing unit, data processing and analysis module composed of multiple resistivity sensors, integrates adaptive algorithms, intelligent diagnosis and prediction modules, three-dimensional visualization modules, user interaction interfaces, data sharing and cloud service modules, automatic survey path planning modules, power management modules, and safety and reliability assurance modules. The data acquisition module uses multiple resistivity sensors to capture the resistivity data of underground rock masses in real time, and the signal processing unit filters, amplifies and digitizes these data to ensure the accuracy and availability of the data; the data processing and analysis module uses adaptive algorithms to conduct in-depth analysis of the data, and the intelligent diagnosis and prediction module further uses machine learning technology to analyze the underground structure. The structure is used for intelligent identification and trend prediction; the analysis results are converted into a three-dimensional geological model that can be intuitively understood by users through the three-dimensional visualization module, and displayed on the user interaction interface, so that users can perform real-time monitoring and operation; the data sharing and cloud service module is responsible for securely storing the processed data and supporting remote access, realizing instant data sharing and team collaboration; the automated survey path planning module dynamically adjusts the survey strategy according to survey needs and environmental feedback, and the guiding data acquisition module efficiently completes the survey task; the power management module provides stable and lasting energy support for the system, and the safety and reliability assurance module ensures the stable operation of the system in various environments through multiple protection measures.

2. The system according to claim 1, characterized in that The data acquisition module also includes a global positioning system (GPS) unit for synchronizing acquisition time stamps.

3. The system according to claim 1 or 2, characterized in that: The signal processing unit further comprises an analog-to-digital converter (ADC) for signal digitization.

4. The system according to any one of claims 1 to 3, characterized in that: The data processing and analysis module further includes an algorithm for data fusion, which is used to integrate data from different sensors.

5. The system according to any one of claims 1 to 4, characterized in that: The intelligent diagnosis and prediction module also includes a deep learning network for pattern recognition.

6. The system according to any one of claims 1 to 5, characterized in that: The 3D visualization module also includes a graphics processing unit (GPU) for geological model rendering.

7. The system according to any one of claims 1 to 6, characterized in that: The user interaction interface also includes a touch screen and physical buttons for receiving user input.

8. The system according to any one of claims 1 to 7, characterized in that: The data sharing and cloud service module also includes a server for data synchronization and version control.

9. The system according to any one of claims 1 to 8, characterized in that: The automated survey path planning module also includes a laser radar (LiDAR) sensor for environmental perception.

10. A method for surveying using the underground rock mass intelligent surveying system based on high-density resistivity as claimed in any one of claims 1 to 9, characterized in that: The following steps are involved: S1. Initialize the survey task and configure system parameters; S2. Deploy data acquisition modules to collect multi-point synchronous high-density resistivity data; S3. Filtering and digitizing the collected signal using a signal processing unit; S4. Perform data fusion and real-time analysis through data processing and analysis modules; S5. Use the intelligent diagnosis and prediction module to perform intelligent diagnosis and prediction of underground rock structure and properties; S6. converting the analysis results into a three-dimensional geological model through a three-dimensional visualization module; S7. Displaying the survey results through the user interaction interface and receiving user input and operation instructions; S8. Use data sharing and cloud service modules for remote data access and team collaboration; S9. Guide the movement and survey of the survey equipment according to the planning results of the automated survey path planning module; S10. Monitor the power management module to ensure stable operation of the system; S11. Use the safety and reliability assurance module to perform fault self-diagnosis and automatic recovery; S12. Analyze the survey results and generate a survey report to provide a basis for subsequent decision-making.

Images