Engineering investigation digital drilling machine based on Internet of Things sensing technology and big data service system

Abstract

The invention is suitable for the technical field of engineering investigation, and provides an engineering investigation digital drilling machine based on the Internet of Things sensing technology and a big data service system.The digital drilling machine comprises a drill tower, a hydraulic standard penetration piece, a slurry pump, an integrated operation table, a double-clamping structure, a power head, monitoring equipment and other assemblies; linkage and data interaction of all the assemblies are achieved through a controller special for engineering machinery. The big data service system covers three aspects of a data architecture, a core algorithm and a security mechanism, the data architecture comprises an edge computing layer and a cloud analysis layer, the core algorithm comprises a drilling efficiency prediction model and equipment health degree evaluation, and the security mechanism comprises data encryption and access control. The big data service system provides intelligent decision support and service for engineering investigation, and the engineering investigation efficiency and quality are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of engineering surveying technology, and in particular to a digital drilling rig and big data service system for engineering surveying based on Internet of Things (IoT) sensing technology. Background Technology

[0002] In the field of engineering surveying, traditional drilling rigs have many shortcomings. On the one hand, traditional drilling rigs rely on manual measurement, resulting in a data error rate as high as 15%-20%. Under complex geological conditions (such as karst caves and fractured zones), the reading error rate can even rise to over 30%. For example, in a highway construction project in a mountainous area, the large measurement errors of traditional drilling rigs led to misjudgments of underground karst caves, ultimately resulting in a ground collapse accident during construction, which not only delayed the project but also caused huge economic losses. On the other hand, the exploration data generated during drilling is stored discretely, with a utilization rate of less than 30%, making it impossible to establish a quantitative model of geological parameters and drilling efficiency. For example, in a subway construction project in a large city, because the exploration data was scattered across different departments and systems, it was difficult to effectively integrate and analyze it, leading to multiple encounters with geological anomalies during construction and an inability to adjust the construction plan in a timely manner.

[0003] Therefore, it is necessary to provide a digital drilling rig and big data service system for engineering exploration based on Internet of Things sensing technology to solve the above-mentioned technical problems. Summary of the Invention

[0004] This invention provides a digital drilling rig and big data service system for engineering exploration based on Internet of Things sensing technology, aiming to reduce the error of drilling equipment exploration data and effectively integrate and analyze exploration data.

[0005] This invention is implemented as follows: a digital drilling rig for engineering exploration based on IoT sensing technology, comprising: a drilling tower, adopting an integral structure to provide stable support and a working platform for the entire drilling rig; a hydraulic standard penetration test (SPT) unit, installed on the drilling tower, used for automatic SPT operations, which is easy to operate and can automatically record data; a mud pump, with a rotatable base for easy maintenance, used to provide stable mud circulation for the drilling process; an integrated control panel, which centrally controls various operations of the drilling rig, simplifies the operation process, and improves work efficiency; a dual-clamping structure, which can adaptively adjust the clamping force to ensure the drill rod is clamped safely and can be locked; a power head, adopting a dual-motor + gearbox power head, with high torque, which can flexibly switch between high and low speeds to meet the needs of different drilling conditions; steel tracks, which can be adjusted for high-speed and low-speed travel via remote control; and monitoring equipment, including a 360° no-blind-spot monitoring camera connected to an intelligent integrated module, which can record the drilling rig's working scene and data in real time and upload the data in real time.

[0006] Preferably, the dual-clamping structure uses a clamping pressure sensor to detect the dual clamping pressure, accurately analyze the operation process, and achieve adaptive adjustment of the clamping force.

[0007] Preferably, the power head is also equipped with a power head pressure and speed sensor to measure the power head pressure and speed, and intelligently detect the working conditions.

[0008] Preferably, the intelligent integration module of the monitoring equipment has a built-in high-precision Beidou satellite positioning system, which has high positioning accuracy and complies with the Ministry of Transport's 808 protocol.

[0009] Preferably, the hydraulic standard penetration test component is equipped with a non-contact depth sensor to detect the depth of each standard penetration test and to intelligently determine the operation result.

[0010] This invention proposes an engineering survey big data service system based on IoT sensing technology. The big data service system is applied to the aforementioned digital drilling rig for engineering survey based on IoT sensing technology. The big data service system includes three aspects: a. Data architecture, including: ① Edge computing layer: The edge computing layer is deployed based on a lightweight convolutional neural network of MobileNetV3, with model parameters compressed by 70% compared to traditional CNNs, adapting to the limited computing power of edge computing nodes. By collecting more than 20 types of working condition data such as drilling rig vibration, oil temperature, and motor current in real time, feature extraction and initial fault judgment are completed at the edge, supporting offline operation and meeting the equipment status monitoring needs in field scenarios without network access. In shale gas horizontal well drilling, the edge computing layer identifies abnormal fluctuations in drill pipe torque in real time and provides an early warning of drill string fatigue fracture risk 10 minutes in advance. ② Cloud analytics layer: A knowledge graph containing over 3 million geological samples was constructed, integrating drilling depth, cuttings composition, sonic logging data, and historical engineering cases. Intelligent lithology classification was achieved through graph neural networks. Simultaneously, a three-dimensional virtual model of the drilling rig was built based on digital twin technology, mapping the physical state of over 100 key components in real time, and predicting component wear trends through finite element analysis. b. Core algorithms, including: ① Drilling efficiency prediction model: The model utilizes LSTM memory units to capture the temporal dependence of drilling efficiency and outputs the predicted drilling speed for the next 2 hours. The model supports dynamic updates, automatically injecting new data for iterative optimization every 50 meters of drilling. By predicting drilling resistance, the power head speed and pump displacement are automatically adjusted. ② Equipment health assessment: The system constructs physical failure models for key equipment components, combines real-time vibration signals, temperature data, and historical maintenance records, and estimates the remaining service life using a particle filtering algorithm. When the health of a component falls below 30%, the system automatically generates a maintenance work order and pushes it to the equipment supplier. This transforms traditional "post-event maintenance" into "72-hour advance warning." The system also establishes equipment health records to support residual value assessment of used equipment and provide data support for equipment leasing / replacement. c. Security mechanisms, including: ① Data encryption: A hybrid encryption system combining the SM4 algorithm and quantum key distribution is adopted: Transmission layer: Dynamic quantum keys are generated via QKD to encrypt drilling data; Storage layer: The SM4 algorithm is used to encrypt and store cloud data. ②Access control: A permission management system is built based on a consortium blockchain, which writes user roles, data types, and operation permissions into smart contracts to achieve fine-grained permission control.

[0011] Compared with related technologies, the digital drilling rig and big data service system for engineering survey based on Internet of Things sensing technology provided by this invention has the following beneficial effects: The digital drilling rig for engineering exploration of this invention has a scientific and reasonable structure, with powerful and well-coordinated components, which can effectively improve the efficiency and quality of drilling operations and provide a stable and reliable data acquisition foundation for engineering exploration.

[0012] 2. The big data service system, through a multi-layered architecture, enables comprehensive data collection, high-speed transmission, precise processing, and in-depth analysis, providing intelligent decision support and services for engineering survey projects. This helps optimize engineering design and construction plans, reduce engineering risks, and improve the economic benefits of engineering projects.

[0013] 3. This system adopts a combination of edge computing and cloud computing, which can realize real-time and rapid data preprocessing and preliminary analysis, as well as in-depth data mining and knowledge discovery, giving full play to the advantages of both and improving the efficiency and quality of data processing.

[0014] 4. The various functions in this system, such as intelligent classification of geological parameters, drilling efficiency prediction, and equipment health management, provide comprehensive intelligent services for engineering exploration, helping to predict and solve potential problems in advance and ensuring the smooth progress of engineering exploration. Attached Figure Description

[0015] Figure 1 A structural configuration diagram of a digital drilling rig for engineering survey based on Internet of Things sensing technology is provided for this invention. Figure 2 This is a schematic diagram illustrating the digital drilling rig data transmission and application in this invention; Figure 3 This is a flowchart of the big data solution in this invention; Figure 4 This is a technical architecture diagram of the big data solution in this invention.

[0016] The following are labeled in the diagram: 11. Drill tower; 12. Hydraulic standard penetration test component; 13. Mud pump; 14. Integrated control panel; 15. Double clamping structure; 16. Power head; 17. Monitoring equipment; 18. Steel tracks. Detailed Implementation

[0017] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0018] This invention provides a digital drilling rig for engineering surveying based on Internet of Things (IoT) sensing technology, such as... Figure 1 As shown, it includes: Drilling rig 11 adopts an integral structure, possessing high strength and stability, capable of withstanding various loads during drilling, providing solid support and a stable working platform for the entire drilling rig. Its rational structural design facilitates installation and disassembly, adapting to engineering survey needs under different terrain and environmental conditions; The hydraulic standard penetration test (SPT) unit 12, installed on the drilling rig, is equipped with the function of automatically performing SPT operations. Powered by a hydraulic system, it ensures the accuracy and efficiency of the SPT operation. During the SPT process, relevant data is automatically recorded, providing accurate data for subsequent geological analysis. The hydraulic SPT unit 12 is equipped with a non-contact depth sensor to detect the depth of each SPT operation, enabling intelligent judgment of the results.

[0019] The mud pump 13 features a rotatable base for easy maintenance and provides a stable and sufficient mud circulation for the drilling process. The flow rate of the mud pump can be adjusted according to drilling conditions to meet the drilling needs of different formations, while also possessing good wear resistance and reliability to ensure stable operation over long periods. The integrated control panel 14 centrally controls various operations of the drilling rig, simplifying the complex operation process. Operators can easily control the drilling rig's start, stop, feed, and lifting actions through this control panel, reducing the difficulty of operation and the error rate, and improving work efficiency. The dual clamping structure 15 can adaptively adjust the clamping force to ensure the drill pipe is clamped safely and can be locked. The dual clamping structure 15 uses a clamping pressure sensor to detect the dual clamping pressure, accurately analyze the operation process, and achieve adaptive adjustment of the clamping force.

[0020] The Power Head 16 employs a dual-motor + gearbox power head, possessing high torque output capability to meet the drilling needs of hard formations. It also allows for flexible switching between high and low speeds to adapt to different drilling speed requirements and conditions, thus improving drilling efficiency. The Power Head 16 is also equipped with a power head pressure and speed sensor to measure pressure and speed, intelligently detecting operating conditions. The power head speed is infinitely adjustable from 0-300 rpm, representing an industry-first dual-motor collaborative drive technology.

[0021] The steel tracks 18 are remotely controlled and can be adjusted to travel at high or low speeds. The monitoring equipment 17 features omnidirectional surveillance cameras connected to an intelligent integration module, enabling comprehensive recording of drilling rig operations and full monitoring of the entire process. The intelligent integration module fuses the collected video data with data from other sensors and uploads it to a cloud server in real time for remote monitoring and management. Simultaneously, the monitoring equipment incorporates a high-precision BeiDou satellite positioning system, ensuring high positioning accuracy and adhering to the Ministry of Transport's 808 protocol, guaranteeing accurate acquisition and transmission of drilling rig location information. Furthermore, its positioning accuracy, achieved through BeiDou + UWB fusion positioning, is ≤±2cm, resolving the issue of single-signal signal obstruction. In addition, digital drilling rigs are also equipped with laser interferometric depth sensors and piezoelectric ceramic-fiber composite pressure sensors to collect drilling depth and formation pressure.

[0022] This invention also proposes an engineering survey big data service system based on IoT sensing technology. The big data service system is applied to the aforementioned digital drilling rig for engineering survey based on IoT sensing technology. The big data service system includes three aspects: (1) Data architecture, including: ① Edge computing layer: (Lightweight AI-driven localized intelligence) Deploying a lightweight convolutional neural network based on MobileNetV3, the model parameter size is compressed by 70% compared to traditional CNNs, adapting to the limited computing power of edge computing nodes (CPU ≤ 4 cores, memory ≤ 8GB); by collecting more than 20 types of working condition data such as drilling rig vibration, oil temperature, and motor current in real time (sampling frequency 100Hz), feature extraction (such as identification of abnormal bearing vibration frequency) and initial fault judgment are completed at the edge, with an average response time ≤ 200ms, reducing latency by 80% compared to cloud processing; the model inference power consumption is ≤ 5W, supporting offline operation (continuous operation for 4 hours when the network is disconnected), meeting the equipment status monitoring needs in field scenarios without network access; in shale gas horizontal well drilling, the edge computing layer identifies abnormal fluctuations in drill pipe torque in real time (threshold ±15%), providing an early warning of drill string fatigue fracture risk 10 minutes in advance, increasing the probability of detecting faults 90% earlier than manual inspection. ② Cloud-based analytics layer: (In-depth analysis of the fusion of knowledge graphs and digital twins) A knowledge graph containing over 3 million geological samples was constructed, integrating drilling depth, cuttings composition, sonic logging data, and historical engineering cases. Intelligent lithology classification was achieved using graph neural networks (GNNs), achieving an accuracy rate of 92% (compared to an average of 75% for manual identification). Simultaneously, a 3D virtual model of the drilling rig was built based on digital twin technology, mapping the physical state of over 100 key components (such as mud pump pistons and winch gears) in real time. Finite element analysis was used to predict component wear trends. The knowledge graph supports cross-project data reuse, allowing for rapid access to drilling parameters (such as drill bit selection and drilling speed) for similar formations when operating in new areas, reducing parameter debugging time by 40%. The synchronization error between the digital twin and the physical drilling rig is ≤2%, achieving closed-loop management of "visualized drilling process - predictable equipment failure - optimizable process parameters." (2) Core algorithms, including: ① Drilling efficiency prediction model (LSTM neural network): The model utilizes 15-dimensional time-series data, including formation hardness (derived from acoustic data inversion), drilling rig speed, pump pressure, and drill bit wear, to capture the temporal dependence of drilling efficiency using an LSTM memory unit. It outputs predicted drilling speeds for the next two hours with a prediction error of ≤±5%. The model supports dynamic updates, automatically injecting new data for iterative optimization after every 50 meters of drilling. Daily drilling tasks are dynamically adjusted based on prediction results to avoid delays caused by efficiency fluctuations, such as by pre-stocking spare drill bits in hard rock formations. By predicting drilling resistance, the model automatically adjusts the power head speed and pump displacement, reducing energy consumption by 12% compared to manual experience-based control. ② Equipment health assessment (digital twin + RUL prediction): Physical failure models of key equipment components (such as hydraulic pumps and gearboxes) are constructed. Combining real-time vibration signals (acquired by accelerometers, accuracy ±0.1g), temperature data (measured by thermocouples, error ±1℃), and historical maintenance records, the remaining useful life (RUL) is estimated using a particle filter algorithm with a prediction error ≤8%. When a component's health level falls below 30%, the system automatically generates a maintenance work order and pushes it to the equipment supplier. This transforms traditional "reactive maintenance" into "72-hour advance warning," reducing unplanned downtime by 60% and lowering single maintenance costs by 40%. Equipment health records are established to support residual value assessment of used equipment (error ≤5%), providing data support for equipment leasing / replacement. (3) Security mechanisms, including: ① Data encryption: (National cryptographic level security protection) A hybrid encryption system combining the SM4 algorithm and quantum key distribution (QKD) is employed: The transmission layer uses QKD to generate dynamic quantum keys (with a 1-minute key update cycle) to encrypt drilling data (such as geological stratification data and equipment operating parameters), enhancing resistance to quantum computing attacks by 100 times. The storage layer uses the SM4 algorithm to encrypt and store cloud data, meeting Level 3 requirements of GB / T39786-2021 "Information Security Technology - Basic Requirements for Cryptographic Applications in Information Systems." This reduces the risk of data transmission leakage by 99%, successfully resisting advanced persistent threat (APT) attacks in a petrochemical project and ensuring the security of oil and gas exploration data. ②Access control: (Blockchain smart contracts) A permission management system built on a consortium blockchain is implemented, which writes user roles (surveying unit / equipment supplier / regulatory agency), data types (real-time operating conditions / historical reports / design drawings), and operation permissions (view / download / modify) into smart contracts to achieve fine-grained permission control (the principle of least privilege, such as supervision units only being able to view quality inspection data). This meets the requirements of the "Regulations on the Security Protection of Critical Information Infrastructure" and automatically passes data security audits in government-invested projects. In multi-unit joint survey projects, smart contracts automatically authorize partners to access designated data, improving data sharing efficiency by 50% with zero data leakage incidents.

[0023] Figure 2 The demonstration showcased the data transmission and application process of a digital prototype for engineering surveying. First, the digital prototype collected multi-dimensional data at the work site using various sensors (such as depth sensors, pressure sensors, and 360° monitoring cameras), including drilling depth, trajectory, formation pressure, power head speed, torque, fuel consumption, and operational footage. After initial processing, this data was transmitted to an edge computing unit via wired networks (such as industrial Ethernet) and wireless networks (such as 5G) for further data cleaning, feature extraction, and preliminary analysis. Next, key data was transmitted to a cloud server via high-speed communication links such as 5G slicing networks for in-depth data storage, analysis, and mining. The cloud server utilized big data analytics (such as LSTM model analysis of the correlation between drilling efficiency and geological parameters) and artificial intelligence algorithms (such as neural networks for intelligent lithology classification) to generate various intelligent application services, including intelligent drilling parameter optimization suggestions, equipment health management strategies, geological modeling and prediction, engineering data sharing and collaboration, and safety management early warnings. These services provide scientific basis and decision support for all aspects of engineering surveying projects, achieving data-driven intelligent management of engineering surveying.

[0024] Figure 3This paper presents a big data solution for engineering surveying. The solution aims to achieve intelligent decision-making and optimization in engineering surveying, using data as the core driving force. It integrates massive engineering surveying data resources, including multi-source heterogeneous sensor data (such as depth, pressure, and rotational speed data), geological sample data (rock cuttings composition, sonic logging data, etc.), historical engineering case data, and equipment operation data, constructing a complete data chain encompassing data acquisition, transmission, storage, processing, analysis, and application. Utilizing advanced big data processing technologies (such as distributed storage, parallel computing, and real-time stream processing) and intelligent analysis algorithms (such as machine learning, deep learning, and graph neural networks), it performs in-depth data mining and knowledge discovery. On the one hand, it provides precise parameter optimization suggestions, intelligent geological condition classification, and drilling efficiency prediction for drilling operations in engineering surveying, improving drilling efficiency and quality. On the other hand, it enables equipment health monitoring, fault early warning, and preventative maintenance, reducing equipment failure risks and maintenance costs. Meanwhile, by leveraging a data sharing and collaboration platform, data barriers between different stages of engineering surveying are broken down, promoting information exchange and collaboration among different departments and project teams, and improving the overall management efficiency and scientific decision-making of the project. Furthermore, emphasis is placed on data security protection, employing encryption, access control, and other technologies to ensure the security and reliability of data during collection, transmission, storage, and use, providing comprehensive support for the digital transformation and intelligent development of engineering surveying.

[0025] Figure 4 The technical architecture of the big data solution for engineering surveying is described, which mainly consists of the following layers: 1. Equipment Layer (Data Acquisition Layer): Deployed on the digital drilling rig for engineering surveys, this layer encompasses various sensors such as laser interferometric depth sensors, piezoelectric ceramic-fiber composite pressure sensors, power head speed sensors, torque sensors, and fuel consumption sensors, as well as equipment like 360° monitoring cameras, dedicated controllers for engineering machinery, and a high-precision BeiDou satellite positioning system. It is responsible for real-time acquisition of multi-dimensional raw data, including drilling depth, formation pressure, power head speed, torque, fuel consumption, video footage, and location information. It also collects standard penetration depth (SPT) data through non-contact detectors, providing a comprehensive, accurate, and real-time data foundation for subsequent data processing and analysis. Simultaneously, the data acquisition layer enables linkage and data interaction between various drilling rig components (such as the drilling tower, hydraulic SPT components, high-flow mud pump, integrated control panel, dual-clamping structure, and power head) and sensors, ensuring the integrity and consistency of data acquisition.

[0026] 2. Data Transmission Layer: Based on 5G communication technology and time-sensitive networking, a high-speed, stable, and reliable data transmission channel is constructed. On the one hand, various types of data acquired by the data acquisition layer are transmitted to the edge computing layer in real time and accurately; on the other hand, key data processed by the edge computing layer is further transmitted to the cloud computing layer, ensuring the timeliness and integrity of data transmission and meeting the high real-time requirements of engineering survey big data.

[0027] 3. Edge Computing Layer: Lightweight AI-driven localized intelligent computing nodes are deployed at the edge, close to the data source. Lightweight convolutional neural networks (such as MobileNetV3) are used to perform real-time feature extraction and preliminary fault diagnosis on over 20 types of operating data, including drilling rig vibration, oil temperature, and motor current. The average response time is ≤200ms, reducing latency by 80% compared to cloud processing. The edge computing layer not only enables preliminary data processing and analysis, alleviating the computing pressure on the cloud, but also has offline operation capabilities (continuous operation for 4 hours without network access), meeting the equipment status monitoring needs in field scenarios without network access, and providing real-time, rapid, localized intelligent services for engineering surveys.

[0028] 4. Cloud Computing Layer: A geological knowledge graph containing over 3 million geological samples is constructed, integrating heterogeneous data from multiple sources such as drilling depth, cuttings composition, sonic logging data, and historical engineering cases. Intelligent lithology classification is achieved through Graph Neural Networks (GNNs), achieving an accuracy rate of 92%. Simultaneously, a 3D virtual model of the drilling rig is built based on digital twin technology, mapping the physical state of over 100 key components (such as mud pump pistons and winch gears) in real time. Finite element analysis is used to predict component wear trends, enabling equipment health assessment and remaining useful life (RUL) prediction with a prediction error ≤8%. Furthermore, the cloud computing layer utilizes Long Short-Term Memory (LSTM) networks to construct a drilling efficiency prediction model. Inputting 15-dimensional time-series data such as formation hardness (derived from sonic logging data), drilling rig speed, pump pressure, and drill bit wear, it predicts the drilling speed for the next 2 hours with a prediction error ≤±5%, providing accurate drilling progress prediction and decision support for engineering exploration projects.

[0029] 5. Data Application Layer: This layer transforms the various analysis results and knowledge generated by the cloud computing layer into practical engineering application value, providing comprehensive intelligent services for engineering survey projects. Specifically, it includes functional modules such as intelligent classification and modeling of geological parameters, optimization and prediction of drilling efficiency, equipment health management and maintenance, engineering data sharing and collaboration, and safety management early warning and response. These modules help engineers better understand underground geological conditions, optimize drilling process parameters, improve equipment operating efficiency and reliability, reduce engineering risks, and achieve intelligent decision-making and management in engineering surveys.

[0030] 6. Data Security Layer: A hybrid encryption system combining the SM4 algorithm and quantum key distribution (QKD) is employed to encrypt and protect data transmission and storage. At the transmission layer, dynamic quantum keys (with a 1-minute key update cycle) are generated via QKD to encrypt drilling data (such as geological stratification data and equipment operating parameters), improving resistance to quantum computing attacks by 100 times. At the storage layer, the SM4 algorithm is used to encrypt cloud data, meeting the Level 3 requirements of GB / T39786-2021 "Information Security Technology - Basic Requirements for Cryptographic Applications in Information Systems," effectively reducing the risk of data transmission leakage. Simultaneously, a permission management system is built based on a consortium blockchain, writing user roles, data types, and operation permissions into smart contracts to achieve fine-grained permission control, meeting the requirements of the "Regulations on the Security Protection of Critical Information Infrastructure," ensuring secure data sharing and legal use, and providing robust data security for engineering survey big data solutions.

[0031] The entire big data solution has a well-defined technical architecture with close collaboration between layers, enabling intelligent processing of the entire process from data collection to data application, and providing strong technical support for the digital transformation and intelligent upgrading of the engineering survey field.

[0032] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit the scope of protection of the invention. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on these embodiments, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art can still combine, add, delete, or otherwise adjust the features of the various embodiments of the present invention according to the circumstances without conflict or creative effort, thereby obtaining different technical solutions that do not fundamentally depart from the concept of the present invention. These technical solutions also fall within the scope of protection of the present invention.

Claims

1. An engineering investigation digital drilling rig based on Internet of Things sensing technology, characterized in that, The drilling rig comprises a drilling tower, a hydraulic standard penetration device, a mud pump, an integrated operation platform, a double-clamping structure, a power head, a steel track, and a monitoring device. The drilling tower is integrally formed and provides stable support and an operation platform for the entire drilling rig. The hydraulic standard penetration device is installed on the drilling tower and can automatically perform standard penetration operations with ease and automatically record data. The mud pump has a rotatable base for easy maintenance and provides stable mud circulation for the drilling process. The integrated operation platform centrally controls various operations of the drilling rig, simplifies the operation process, and improves work efficiency. The double-clamping structure can self-adaptively adjust the clamping force to ensure safe clamping of the drill pipe and locking. The power head uses a double-motor + gear box power head, has large torque, can flexibly switch between high and low speeds, and meets the needs of different drilling conditions. The steel track can be adjusted to high and low speeds through remote control. The monitoring device comprises a 360° dead-angle-free monitoring camera connected to an intelligent integrated module, can record the drilling rig operation scene and data in real time, and uploads the data in real time.

2. The internet-based sensing technology-based engineering survey digital drilling rig according to claim 1, characterized in that, The double-clamping structure detects the double-clamping pressure through a clamping pressure sensor, accurately analyzes the operation process, and self-adaptively adjusts the clamping force.

3. The internet-based sensing technology based engineering survey digital drilling rig according to claim 1, characterized in that, The power head is also equipped with a power head pressure and speed sensor for measuring the power head pressure and speed and intelligently detecting the working condition.

4. The internet-based sensing technology based engineering survey digital drilling rig according to claim 1, characterized in that, The intelligent integrated module of the monitoring device is built-in with a high-precision Beidou satellite positioning system, has high positioning accuracy, and follows the 808 protocol of the Ministry of Transport.

5. The internet-based sensing technology based engineering survey digital drilling rig according to claim 1, characterized in that, The hydraulic standard penetration device is equipped with a non-contact depth sensor for detecting the depth of each standard penetration and intelligently judging the operation result.

6. An engineering investigation big data service system based on Internet of Things sensing technology, characterized in that, The big data service system is applied to the engineering survey digital drilling rig based on the Internet of Things sensing technology in any one of claims 1-5, and comprises three aspects: a. Data architecture, including: ① Edge computing layer: The deployment of the edge computing layer is based on the lightweight convolutional neural network of MobileNetV3, which compresses the model parameter size by 70% compared with traditional CNN, and adapts to the limited computing power of edge computing nodes; through real-time collection of 20+ types of working condition data such as drilling rig vibration, oil temperature, and motor current, feature extraction and fault preliminary judgment are completed at the edge, supporting offline operation to meet the equipment state monitoring needs in network-free outdoor scenes; in shale gas horizontal well drilling, the edge computing layer can identify abnormal fluctuations in drill pipe torque in real time and give 10-minute early warning of the risk of drill tool fatigue fracture; ② Cloud analysis layer: A knowledge graph containing 3 million geological samples is constructed, which integrates drilling depth, rock composition, acoustic logging data, and historical engineering cases, and realizes intelligent classification of lithology through graph neural networks; at the same time, a three-dimensional virtual model of the drilling rig equipment is constructed based on digital twinning technology, which can real-time map the physical state of 100+ key components and predict the component wear trend through finite element analysis; b. Core algorithm, including: ① Drilling efficiency prediction model: LSTM memory cells are used to capture the time sequence dependence of drilling efficiency, and the predicted value of drilling speed in the next 2 hours is output; the model supports dynamic updating, and new data is injected for iteration optimization every 50 meters of drilling; by predicting the drilling resistance, the speed of the power head and the pump displacement are automatically adjusted; ② Equipment health assessment: Build a physical failure model of the key components of the equipment, combine real-time vibration signals, temperature data and historical maintenance records, and estimate the remaining useful life through the particle filtering algorithm; when the component health is less than 30%, the system automatically generates a maintenance work order and pushes it to the equipment supplier; change the traditional "after-maintenance" to "72-hour early warning"; establish an equipment health file to support the residual value assessment of second-hand equipment and provide data support for equipment leasing / replacement; c. Security mechanisms, including: ① Data encryption: Adopting a hybrid encryption system of "SM4 algorithm + quantum key distribution": at the transmission layer, generate dynamic quantum keys through QKD to encrypt drilling data; at the storage layer, use the SM4 algorithm to encrypt and store cloud data; ② Access control: Based on the alliance chain, build a permission management system, write user roles, data types and operation permissions into smart contracts, and realize fine-grained permission control.

Images