An intermittent spiral tunneling machine and its control method

Abstract

This invention provides an intermittent auger tunneling machine and its control method, relating to the field of engineering machinery technology. The invention first uses tunneling parameters as feedback to perform PI calculations on the control parameters, obtaining the initial control parameters for the next cycle. This considers the influence of ground resistance, rotational torque, and vibration, ensuring the initial control parameters adapt to the actual conditions of the current tunneling face. Subsequently, the invention optimizes the initial control parameters using a preset optimization model. Since the preset optimization model is trained based on historical tunneling and control parameters, it fully considers the actual control conditions during the tunneling process over a historical period, making the target control parameters more consistent with the actual conditions of the current tunneling face. This improves the control accuracy of the auger tunneling machine, achieving high-precision control, avoiding drill bit deviation and torque instability problems, and improving the tunneling efficiency of the auger tunneling machine.

Description

Technical Field

[0001] This invention relates to the field of engineering machinery technology, and in particular to an intermittent spiral tunneling machine and its control method. Background Technology

[0002] In engineering fields such as tunnel boring, mining, and underground pipeline construction, widely used tunneling machines mainly include shield tunneling machines, full-face tunneling machines, and horizontal auger drilling rigs. These devices are typically used to excavate rock, soil, and other strata, and mechanically complete tunnel boring or underground engineering drilling operations. However, existing tunneling equipment suffers from severe deviations in tunneling paths and low tunneling efficiency when operating under complex geological conditions (such as multi-layered geological structures, hard rock strata, and uneven geology).

[0003] The complex and varied geological environment within tunnels leads to inaccurate control of the drill bit's position, angle, and path. For example, soft soil layers and hard rock layers require different drill bit thrusts, and the uneven geological conditions in different areas ahead of the tunnel result in varying thrusts and rotation speeds. When using thrusts and rotation speeds adapted to soft soil layers to handle hard rock layers, problems such as drill bit deviation and unstable torque can easily occur, causing the tunneling path to deviate from the predetermined target and reducing tunneling efficiency. Summary of the Invention

[0004] This invention provides an intermittent spiral tunneling machine and its control method, which can achieve high-precision control of the spiral tunneling machine and improve its tunneling efficiency.

[0005] In a first aspect, the present invention provides a control method for an intermittent auger tunneling machine, the intermittent auger tunneling machine comprising an auger drilling rig module, a sensor module, and a control module. The method includes: detecting tunneling parameters and control parameters of the auger drilling rig module; the tunneling parameters including ground resistance, rotational torque, vibration frequency, and vibration amplitude; the control parameters including thrust, rotational speed, and drilling path; using the tunneling parameters as feedback, performing PI calculation on the control parameters to obtain initial control parameters for the next cycle; optimizing the control parameters based on the tunneling parameters, control parameters, initial control parameters, and a preset optimization model to obtain target control parameters for the next cycle; the preset optimization model being trained based on tunneling parameters and control parameters from historical periods; and controlling the micro-horizontal auger drilling rig module to tunnel based on the target control parameters.

[0006] Secondly, embodiments of the present invention provide a control module for an intermittent auger tunneling machine. The control module includes: a communication unit for detecting the tunneling parameters and control parameters of the auger module; the tunneling parameters include ground resistance, rotational torque, vibration frequency, and vibration amplitude; the control parameters include thrust, rotational speed, and drilling path; a processing unit for performing PI calculations on the control parameters using the tunneling parameters as feedback to obtain initial control parameters for the next cycle; optimizing the control parameters based on the tunneling parameters, control parameters, initial control parameters, and a preset optimization model to obtain target control parameters for the next cycle; the preset optimization model is trained based on tunneling parameters and control parameters from historical periods; and controlling the micro-horizontal auger module to tunnel based on the target control parameters.

[0007] Thirdly, embodiments of the present invention provide an intermittent auger tunneling machine, which includes electronic equipment, the electronic equipment including a memory and a processor, the memory storing a computer program, the processor being used to call and run the computer program stored in the memory to perform the steps of the method as described in the first aspect and any possible implementation thereof.

[0008] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, it implements the steps of the method as described in the first aspect and any possible implementation thereof.

[0009] This invention provides an intermittent auger tunneling machine and its control method. First, using tunneling parameters as feedback, the invention performs PI calculations on the control parameters to obtain the initial control parameters for the next cycle. The effects of ground resistance, rotational torque, and vibration are considered to ensure the initial control parameters adapt to the actual conditions of the current tunneling face. Then, the invention optimizes the initial control parameters using a preset optimization model. Since the preset optimization model is trained based on historical tunneling and control parameters, it fully considers the actual control conditions during the tunneling process over a historical period. This makes the target control parameters more consistent with the actual conditions of the current tunneling face, improving the control accuracy of the auger tunneling machine, achieving high-precision control, avoiding drill bit deviation and torque instability problems, and improving the tunneling efficiency of the auger tunneling machine. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a schematic diagram of the structure of an intermittent spiral tunneling machine provided in an embodiment of the present invention;

[0012] Figure 2 This is a flowchart illustrating a control method for an intermittent spiral tunneling machine according to an embodiment of the present invention;

[0013] Figure 3 This is a schematic diagram of the structure of the control module of an intermittent spiral tunneling machine provided in an embodiment of the present invention;

[0014] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0015] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0016] To make the objectives, technical solutions, and advantages of the present invention clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0017] like Figure 1 As shown, this embodiment of the invention provides an intermittent auger tunneling machine. The intermittent auger tunneling machine includes an auger drilling module, a sensor module, and a control module.

[0018] The auger drilling rig module, also known as the miniature horizontal auger drilling rig module, is used to drive the rotation and propulsion of the auger drill bit. The miniature horizontal auger drilling rig module includes a high-rigidity miniature transmission unit, a servo-controlled electronic drive unit, and a miniature auger drill bit unit.

[0019] The high-rigidity micro transmission unit consists of a multi-stage gear transmission assembly made of high-strength alloy material. This assembly drives the rotation and propulsion of the auger bit through multi-stage precision transmission. Each gear is designed with precise geometric optimization to ensure the transmission system maintains high efficiency and stability under high load conditions. The multi-stage transmission design reduces torque loss at each stage, ensuring the drill bit's rotation and propulsion can adapt to different formation conditions.

[0020] The servo electronic control drive unit monitors the drill bit position and angle in real time through a high-resolution encoder and dynamically adjusts the drill bit's movement in conjunction with a closed-loop control algorithm.

[0021] Closed-loop control algorithms are used to adjust the drill bit's motion path and rotation speed in real time. Closed-loop control refers to correcting operational errors through a feedback system, as shown in the following formula:

[0022]

[0023] Where u(t) is the control output, e(t) is the error between the target value and the actual value, Kp is the proportional gain, Ki is the integral gain, and Kd is the derivative gain.

[0024] For example, embodiments of the present invention can calculate the difference (error) between the current state and the target state of the drill bit in real time based on the drilling speed, torque, and vibration data monitored by sensors. Through a PID algorithm, the control system dynamically adjusts the thrust and drilling speed to keep the drill bit in optimal condition, thereby preventing equipment damage or deviation from the path caused by pressure fluctuations or abnormal torque.

[0025] The miniature auger drill bit unit features a multi-layered wear-resistant alloy coating, increasing the drill bit's lifespan and reducing the risk of wear during drilling. It also incorporates helical cutting edges on the drill bit's surface. The geometry of these cutting edges is carefully designed to efficiently cut different types of geological materials (such as rock and sand) during drilling, and the resulting debris is conveyed along the helical grooves on the drill bit's surface to the chip removal module.

[0026] The geometry of the spiral blade is designed as follows:

[0027] For soft or mixed formations: Helix angle: 35° to 45°. Rake angle: 20° to 25°, clearance angle: 10°. Pitch: 120mm to 150mm. Helix groove depth: 15mm to 20mm. This configuration helps improve cuttings removal efficiency and reduces drill bit friction with the formation, making it suitable for rapid drilling into soft soil or mixed geology.

[0028] Hard formations: Helix angle: 15° to 25°. Rake angle: 5° to 10°, clearance angle: 5° to 8°. Pitch: 30mm to 50mm. Helix groove depth: 5mm to 10mm. This configuration provides better cutting stability and reduces friction and resistance encountered during drilling, making it suitable for rock and hard formations.

[0029] The sensor monitoring module is used to monitor real-time operating parameters such as pressure, torque, and vibration during the drilling process. The sensor monitoring module includes pressure sensors, torque sensors, and vibration sensors.

[0030] A pressure sensor, installed near the drill bit, is used to detect the formation resistance encountered by the drill bit during drilling in real time. When a pressure change is detected, the sensor will feed back to the control module to adjust the thrust or drilling speed to prevent excessive load or drill bit jamming.

[0031] The torque sensor, integrated on the drive shaft, is used to detect real-time torque changes on the drive shaft. The torque sensor data plays an important role in determining whether the drill bit has encountered hard materials in the formation or whether the drill bit is stuck, and is dynamically adjusted through the control system.

[0032] Vibration sensors, installed in the transmission mechanism, are used to detect the frequency and amplitude of vibrations during drilling. Based on the vibration data, the control system can determine whether drilling is stable and adjust drilling parameters or issue fault alarms in a timely manner when abnormal vibrations occur.

[0033] The control module, connected to the sensor monitoring module, is used to adjust the control parameters of the drill bit based on the feedback data from the sensor monitoring module. The control parameters include drilling speed, thrust, and drilling path.

[0034] The control module includes a multi-parameter real-time control unit, an adaptive control unit, a path planning unit, and an anomaly detection unit.

[0035] The multi-parameter real-time control unit adjusts the drill bit's thrust, rotational speed, and drilling path in real time based on pressure, torque, and vibration data fed back from sensors. This unit automatically adjusts the drill bit's thrust, rotational speed, and drilling path according to a control algorithm. This unit can employ fuzzy control algorithms to handle complex drilling conditions. The fuzzy control rules are as follows:

[0036]

[0037] Where u is the control output, μ i It is a membership function, f i This is a control rule. This formula is used to handle control decisions under conditions of uncertainty and fuzziness.

[0038] Implementation of fuzzy control rules: The fuzzy controller outputs appropriate control commands (such as drilling speed and thrust adjustment) based on the input fuzzy variables, such as drill bit pressure, torque, and vibration. Each input variable can be fuzzified into a fuzzy language set such as "low," "medium," and "high" according to its value.

[0039] Example of a rule: Assuming the input variables are "Pressure" and "Torque", and the output variables are "Speed" and "ThrustForce", the fuzzy control rule can be defined as follows:

[0040] Rule 1: If the pressure and torque are high, then the drilling speed and thrust will be low.

[0041] Rule 2: If the pressure is low and the torque is moderate, then the drilling speed is high and the thrust is moderate.

[0042] Rule 3: If the vibration is high, then the drilling speed should be reduced.

[0043] Fuzzy inference process: Based on the data fed back from the current sensors, the fuzzy controller calculates the actual drilling speed and thrust through fuzzification, rule-based inference, and defuzzification. In this way, the tunneling machine can smoothly adjust its operating parameters when the formation conditions are uncertain.

[0044] The adaptive control unit, based on deep learning algorithms, optimizes drilling parameters by analyzing formation feedback data and adjusts them in real time according to the actual drilling conditions. Through a deep neural network (DNN), the adaptive control unit can analyze formation feedback data and adjust the thrust and rotational speed. The loss function of the DNN is defined as follows:

[0045]

[0046] Where L(θ): loss function, representing the error between the neural network's predicted output and the real data; N: number of samples; yi: actual drilling parameters (such as optimal thrust or drilling speed); f(xi; θ): predicted output calculated by the neural network based on the input xi, where θ is the model's weight parameter.

[0047] For example, in the embodiments of the present invention, during the operation of an intermittent auger tunneling machine, the DNN dynamically updates the model parameters θ based on historical drilling data and real-time sensor feedback (such as pressure, torque, and vibration). By minimizing the loss function, the DNN can output more accurate control parameters such as drilling speed and thrust under different geological conditions, ensuring the high efficiency of the equipment in complex formations.

[0048] The path planning unit employs a reinforcement learning algorithm to calculate the real-time optimized drilling path using the Bellman equations. The Bellman equations are as follows:

[0049]

[0050] In this algorithm, V(s) represents the value of state s, i.e., the overall benefit of performing a drilling action under the current geological conditions. R(s,a) is the immediate reward value after performing action a, representing the drilling effect brought about by this action under the current geological conditions (such as smooth path passage, obstacle avoidance, etc.). γ is a discount factor used to balance current and future benefits. P(s′|s,a) is the state transition probability, the probability that the system will transition from state s to state s′ after performing action a, representing possible changes under different geological conditions. This algorithm is used to update the drilling path in real time and avoid obstacles.

[0051] Applications in tunnel boring machines: Reinforcement learning algorithms use data collected by sensors to evaluate the effectiveness of each step in the drilling process and predict the potential impact of different operations (such as adjusting the drill bit angle and changing the thrust). The path planning unit uses this algorithm to adjust the drill bit path in real time to avoid uneven geological formations such as rock fissures and hard obstacles, ensuring the optimization of the drilling path.

[0052] Fuzzy control rules are responsible for outputting adjustment instructions based on the fuzzy language set when real-time feedback data fluctuates, so that parameters such as drilling speed and thrust can be flexibly adjusted under uncertain or complex geological conditions.

[0053] The loss function of the DNN is used to train the adaptive control model, ensuring that the drilling rig adjusts the thrust and drilling speed according to historical data and real-time feedback during actual operation, thereby minimizing drill bit wear and improving drilling efficiency.

[0054] The Bellman equation is used in path planning to calculate the optimal drilling path based on different conditions, in order to bypass complex geological structures and achieve efficient and safe drilling.

[0055] The anomaly detection unit analyzes sensor data using a Support Vector Machine (SVM) model to detect abnormal operating states and automatically adjusts operating parameters. The SVM decision function is:

[0056]

[0057] Where x: input data (such as torque, pressure, vibration), y i The corresponding label (normal or abnormal), α i is the coefficient of the support vector, K(xi,x) is the kernel function used to calculate the similarity between different inputs, and b is the bias.

[0058] Applications in tunneling machines: SVM analyzes real-time data from sensors to identify drill bit wear, transmission system load changes, and abnormal vibration patterns. When an anomaly is detected, the control module automatically adjusts operating parameters and issues an alarm to prevent further damage to the equipment.

[0059] In some embodiments, the adaptive control unit further includes a deep neural network that analyzes formation characteristics through a multilayer perceptron model and adjusts the drilling parameters of the drill bit based on real-time formation feedback data.

[0060] The control module also includes a self-learning unit, which optimizes the parameter adjustment model under different geological conditions based on real-time collected historical drilling data.

[0061] This self-learning unit optimizes the model based on historical drilling data. Through the self-learning algorithm, the unit can continuously improve the system's adaptability to different geological conditions during operation. The self-learning process can be described as follows:

[0062]

[0063] Where θ is the model parameter and η is the learning rate. It is the gradient of the loss function, representing the weight update after each training iteration.

[0064] The intermittent auger also includes an automatic chip removal module. This module is used to remove the debris generated during drilling.

[0065] The automatic chip removal module includes a spiral chip removal unit and an automatic cleaning unit. The spiral chip removal unit, connected to the spiral drill bit, has a high-friction spiral groove structure inside to remove chips during drilling; this structure rotates during drilling to transport chips from the drill bit backward and discharge them through the chip removal channel.

[0066] Integrated design of helical cutting edge and chip removal structure: The helical cutting edge not only cuts the formation material but also performs chip removal. The helical cutting edge is designed with special helical grooves, the geometry of which (such as pitch and groove depth) is carefully designed to smoothly remove the cut debris from the borehole during drilling. The cut rock, soil, and other materials are carried away from the drill bit along the helical grooves and discharged from the borehole through the chip removal channel.

[0067] Double-helix structure: To improve cuttings removal efficiency, the spiral cuttings removal unit can be designed with a double-helix structure, that is, two or more intersecting spiral grooves are arranged on the drill bit. The double-helix design can remove cuttings more quickly during drill bit rotation, while reducing cuttings removal resistance. This design is particularly suitable for use in highly cohesive soils or water-bearing formations.

[0068] chip removal channel

[0069] Channel Design: The chip removal channel is a key component of the automatic chip removal module, and its design directly affects the efficiency of chip removal. The chip removal channel is usually connected to the spiral chip removal unit. The diameter and length of the channel are designed according to the diameter and depth of the drill hole to ensure that chip accumulation or blockage does not occur during chip removal.

[0070] Optimized friction on the inner wall of the chip removal channel: The inner wall of the chip removal channel undergoes special friction treatment to reduce the resistance of chips within the channel and ensure smooth chip removal. The inner wall surface is typically made of low-friction materials, such as coated wear-resistant steel or special plastics, to prevent drill chips from accumulating in the chip removal channel.

[0071] The automatic cleaning unit includes mechanical scrapers and an airflow-assisted chip removal layer to prevent chip buildup in the chip removal channel. The scrapers are used to remove chip debris accumulated in the chip removal channel.

[0072] Mechanical scraper: The automatic cleaning unit is equipped with a mechanical scraper system installed inside the chip removal channel. This system is responsible for periodically cleaning up accumulated debris within the channel. The scraper slides along the inner wall of the channel, physically removing any adhering or accumulated debris. The scraper is made of high-strength, wear-resistant materials, such as cemented carbide or polymer composites, enabling it to operate stably for extended periods in high-wear environments.

[0073] Automatic start-stop mechanism: The cleaning process of the mechanical scraper is controlled by the system's intelligent start-stop mechanism. When the sensor detects that the accumulation of debris in the chip removal channel reaches a certain threshold, the system automatically starts the cleaning unit. As the scraper passes through the chip removal channel, it promptly removes the accumulated debris, preventing blockages caused by debris buildup.

[0074] The automatic chip removal module also includes an airflow assist unit, which is used to assist chip removal with high-pressure gas during drilling, blowing away small debris that is difficult to remove by mechanical means, ensuring that the chip removal channel is always unobstructed, and preventing debris from accumulating in the chip removal channel.

[0075] The airflow-assisted layer provides additional debris removal power through high-pressure gas, making it particularly suitable for deep drilling or environments where debris tends to accumulate. This system effectively disperses fine debris within the channel, preventing blockages.

[0076] High-pressure gas supply system: The airflow auxiliary layer is equipped with a high-pressure gas supply system, typically using compressed air or other gases. The gas enters the chip removal channel through a specially designed airflow channel, and the high-pressure airflow blows the fine chips out of the chip removal channel.

[0077] Adjustable airflow: The airflow-assisted system can dynamically adjust the pressure and velocity of the airflow according to the drilling depth, geological conditions, and debris particle size, ensuring that the airflow-assisted debris removal effect can adapt to different geological conditions. For example, the system may need to increase the airflow velocity when removing clay or wet soil, while the airflow velocity can be appropriately reduced in dry formations.

[0078] Airflow direction optimization: The design of the airflow auxiliary layer takes into account the direction and distribution of airflow. The airflow inlet position and angle are optimized to ensure that the airflow can effectively cover the entire cross-section of the chip removal channel, thereby maximizing the dispersion and cleaning of accumulated debris.

[0079] Sensor monitoring and feedback mechanism

[0080] To ensure that the chip removal module can operate continuously and efficiently under different working conditions, the system is equipped with multiple sensors to monitor the unobstructedness of the chip removal channel.

[0081] Pressure sensor: Installed inside the chip removal channel, it monitors the pressure of discharged chips in real time. If an abnormally high chip removal pressure is detected, the system will automatically activate the airflow assist layer and mechanical scraper.

[0082] Debris flow monitoring sensor: Monitors the flow of debris through the debris discharge channel. When the flow decreases or shows signs of blockage, the system will adjust the debris discharge speed or activate the cleaning device.

[0083] Feedback control mechanism: Based on sensor data feedback, the control system can dynamically adjust the rotation speed of the spiral chip removal unit and the air pressure of the airflow auxiliary layer to ensure that the chip removal channel remains unobstructed at all times.

[0084] Detailed design and data of automatic chip removal module

[0085] Spiral chip removal unit: Spiral groove width: range: 10mm to 30mm. 10mm to 15mm: suitable for hard formations, ensuring that the drill bit strength is not reduced due to excessively wide grooves, while still effectively removing chips.

[0086] 20mm to 30mm: Suitable for softer or mixed formations, where a wider groove can increase the amount of cuttings removed.

[0087] Helical flute depth: Range: 5mm to 20mm (consistent with the design of the helical cutting edge). 5mm to 10mm: Suitable for hard formations; this depth is sufficient to gradually remove chips during cutting without weakening the overall strength of the drill bit. 10mm to 20mm: Suitable for soft formations or mixed geological conditions; the flute depth helps to accelerate chip removal.

[0088] Double-helix design: Number of helices: 2 to 3 helical grooves, staggered on the drill bit surface, enhancing chip removal capability. 2 helical grooves: Suitable for general hard formations, ensuring a stable chip removal path. 3 helical grooves: Suitable for deep or softer formations, increasing the number of chip removal channels and improving chip removal efficiency.

[0089] Chip removal channel: Channel diameter: Range: 50mm to 200mm (specific design based on borehole diameter). 50mm to 100mm: Suitable for small-diameter drilling projects, typically used for smaller-scale boreholes. 100mm to 200mm: Suitable for large-diameter boreholes, especially large-scale projects such as tunnel excavation, ensuring rapid removal of cuttings.

[0090] Channel length: Range: 500mm to 5000mm (designed according to drilling depth). 500mm to 2000mm: Suitable for shallow drilling projects, shorter channel length results in less debris accumulation. 2000mm to 5000mm: Used for deep drilling, longer channels ensure smooth debris removal and prevent clogging even under complex geological conditions.

[0091] Coefficient of friction of the inner wall of the channel: range: 0.15 to 0.30 (using treated low-friction materials).

[0092] Lower coefficient of friction (e.g., 0.15): suitable for efficient chip removal, reducing chip retention in the channel, and is typically used in easily clogged formations such as clay.

[0093] A higher coefficient of friction (e.g., 0.30) is suitable for formations with hard debris. Under such conditions, slightly higher friction helps control the removal of debris without causing blockage.

[0094] Automatic cleaning unit: Mechanical scraper size: Range: Diameter is 90% to 95% of the channel diameter. For example, for a chip removal channel with a diameter of 100mm, the scraper diameter can be 90mm to 95mm to ensure that the scraper can fully contact the inner wall and remove most of the debris.

[0095] Scraper material thickness: Range: 5mm to 10mm. 5mm: Suitable for cleaning soft surfaces; the scraper is lightweight and flexible. 10mm: Suitable for high-intensity chip removal in hard surfaces; wear-resistant and robust.

[0096] Cleaning Cycle: Range: Every 30 to 120 minutes (automatically adjusted based on sensor feedback). 30 minutes: For layers with low chip removal efficiency or rapid chip accumulation, ensuring the channels are not blocked. 120 minutes: Suitable for layers with smooth chip removal, reducing unnecessary cleaning actions.

[0097] Airflow Assist Layer: High-Pressure Gas Pressure: Range: 0.5MPa to 1.5MPa. 0.5MPa to 1.0MPa: Suitable for conventional soft formations; low-pressure airflow can effectively remove fine debris. 1.0MPa to 1.5MPa: Suitable for deep or hard formations; high-pressure airflow can more effectively clean debris from the chip removal channels.

[0098] Airflow velocity: Range: 10 m / s to 30 m / s. 10 m / s to 15 m / s: Suitable for soft, loose soils; a moderate airflow velocity is sufficient to expel debris. 20 m / s to 30 m / s: Used for hard or wet, sticky strata; in these cases, a higher airflow velocity prevents debris from adhering to the channel walls and effectively avoids clogging.

[0099] Airflow direction and angle: The airflow enters the chip removal channel at an angle of 30° to 45°, consistent with the direction of the spiral groove, to ensure that the airflow and the direction of chip discharge are consistent, thereby maximizing the chip removal effect.

[0100] Sensor Monitoring and Feedback Mechanism: Pressure Sensor Monitoring Range: 10 kPa to 100 kPa (for monitoring debris accumulation pressure in the chip removal channel). 10 kPa to 50 kPa: Suitable for relatively smooth chip removal environments, capable of detecting lightly accumulated debris. 50 kPa to 100 kPa: Suitable for environments where the chip removal channel is prone to blockage; the sensor can detect high-pressure accumulation and trigger the cleaning system. Debris Flow Rate Monitoring Sensor Range: 5 kg / h to 100 kg / h (depending on the formation and debris generation rate).

[0101] 5 kg / h to 20 kg / h: Suitable for softer strata or loose soil. 50 kg / h to 100 kg / h: Suitable for hard rock or large-volume debris discharge environments, ensuring the system can adjust the debris discharge rate or activate the airflow auxiliary layer in a timely manner.

[0102] This intermittent spiral tunneling machine also includes a lubrication and cooling module. The lubrication and cooling module is used to maintain the temperature and friction of the tunneling machine within a preset range through cooling and lubrication. The cooling system is responsible for controlling the temperature of the drill bit and servo drive system to prevent equipment failure due to high temperatures. The system adopts a dual-loop structure, cooling key components separately.

[0103] The lubrication and cooling module includes a cooling circuit unit and a lubrication unit. The cooling circuit unit, used to cool the auger bit and servo drive system, consists of a dual-circuit structure, with each circuit serving the cooling needs of a different component. Each circuit is specifically designed to ensure that the cooling requirements of different components are met. The flow rate and temperature of the coolant are regulated by an automatic control system to prevent wear caused by prolonged operation at high temperatures. One circuit is dedicated to cooling the auger bit, and the other is for cooling the servo drive system. Each circuit operates independently and is equipped with sensors and controllers for dynamic temperature regulation.

[0104] Cooling Circuit 1 (Auger Bit): This circuit provides cooling for the drill bit, rapidly absorbing heat during cutting to prevent overheating that could degrade material properties or cause premature cutting edge wear. Coolant Flow Rate: 3L / min to 10L / min (automatically adjusted based on drill bit operating temperature). Lower Flow Rate (3L / min to 5L / min): Suitable for general geological conditions, keeping temperature within acceptable limits. Higher Flow Rate (6L / min to 10L / min): Suitable for high-friction formations or for maintaining stable drill bit temperature during prolonged continuous operation.

[0105] Cooling Circuit 2 (Servo Drive System): Used to cool the servo motor and transmission mechanism. By reducing temperature, it prevents the drive system from failing due to overheating or experiencing accuracy issues. Coolant flow rate: 2L / min to 6L / min (adjustable according to the servo system load). Low flow rate (2L / min to 4L / min): Suitable for servo system operation under normal load. High flow rate (4L / min to 6L / min): Suitable for high-load conditions requiring additional cooling to ensure the servo system does not overheat.

[0106] Coolant temperature control is crucial. The cooling system is equipped with temperature sensors and regulation mechanisms to dynamically adjust the coolant temperature, ensuring it remains within a suitable range. Coolant temperature range: 10°C to 50°C.

[0107] 10℃ to 20℃: Used in high-temperature drilling scenarios to quickly reduce equipment temperature.

[0108] 30℃ to 50℃: The temperature range under normal operation, ensuring that the equipment operates within the optimal range and avoiding material performance degradation.

[0109] Heat recovery device: A heat recovery device can also be integrated into the cooling system to recover the waste heat generated during the operation of the auger drill bit and use it to preheat the coolant, improving energy efficiency. Heat recovery efficiency: 30% to 50%.

[0110] Lower efficiency (30%): Used for general drilling operations, primarily for energy conservation.

[0111] High efficiency (50%): Suitable for long-term working environments, the heat recovery system can effectively reduce energy consumption and lower the cost of coolant temperature regulation.

[0112] The lubrication unit automatically adjusts the lubricant injection volume based on real-time friction monitoring results. Sensors in the lubrication unit monitor the friction conditions in the system in real time and adjust the lubricant injection according to a preset friction coefficient range to ensure continuous and stable operation of the equipment.

[0113] The primary function of a lubrication system is to reduce friction between the drill bit and the formation, as well as between the drill bit and the transmission mechanism, thereby reducing equipment wear and extending equipment life. The lubrication system must be designed to adapt to changes in different geological conditions and ensure that the equipment operates in optimal condition through real-time adjustments.

[0114] Active lubrication unit: The lubrication system automatically adjusts the lubricant injection rate based on real-time data feedback from sensors (such as friction coefficient and temperature) to ensure that the surface friction of the equipment is maintained within a reasonable range. Lubricant is directly sprayed onto the parts of the spiral blade that contact the ground, as well as key components of the transmission system. Lubricant injection rate: 10 mL / min to 50 mL / min.

[0115] 10 mL / min to 20 mL / min: Suitable for soft or low-wear formations with low lubrication requirements.

[0116] 30 mL / min to 50 mL / min: Suitable for highly abrasive or hard surfaces that require more lubricant to reduce friction.

[0117] Lubricant Type: Depending on different geological conditions and operating environments, lubrication systems can use different types of lubricants, such as high-viscosity lubricating oils or solid lubricants. High-viscosity lubricating oils: Suitable for high-load operations, maintaining stable lubrication performance under high temperature and high pressure environments. Viscosity grades: ISO VG 220 to ISO VG 460.

[0118] ISOVG220: Suitable for medium load conditions, it reduces cutting edge wear and ensures smooth drilling.

[0119] ISOVG460: Suitable for high-load, high-temperature operating conditions, especially in hard rock formations, it can effectively protect the transmission system and drill bit.

[0120] Solid lubricants, such as graphite or molybdenum disulfide, are suitable for extreme environments, especially when operating in high-temperature or chemically corrosive environments.

[0121] Sensor monitoring and feedback mechanism: The lubrication and cooling module is equipped with multiple sensors to monitor the friction and temperature conditions during equipment operation, ensuring that the system automatically adjusts the amount of lubricant injected and the flow rate of coolant based on real-time data.

[0122] Temperature sensor: Used to monitor the temperature of the drill bit, servo system, and coolant in real time to ensure that all components remain within their optimal operating temperature range. Temperature sensor measurement range: 0℃ to 150℃. Drill bit temperature monitoring: When the temperature exceeds 60℃, the cooling system automatically increases the flow rate to prevent equipment failure due to overheating. Servo system temperature monitoring: Ensures that the servo motor temperature is kept below 50℃ to avoid efficiency degradation due to overheating.

[0123] Friction Sensor: The friction sensor detects the coefficient of friction between the drill bit and the formation / transmission system, providing timely feedback on the friction status so that the lubrication system can adjust the lubricant injection volume in real time. Friction coefficient monitoring range: 0.05 to 0.50. 0.05 to 0.20: Suitable for environments with low friction and low lubricant requirements. 0.30 to 0.50: Suitable for high-friction environments, such as hard formations or high-load operations; the lubrication system automatically increases the lubricant injection volume.

[0124] The intermittent spiral tunneling machine provided by this invention achieves high-precision control of the drill bit position, angle and drilling path through the precise cooperation of a micro horizontal spiral drilling rig module and a servo electronic control drive system, ensuring stable and efficient operation of the drill bit under various complex geological conditions, which not only improves tunneling efficiency but also extends equipment life.

[0125] This invention, by introducing a deep neural network algorithm and an adaptive control unit, can automatically adjust the drill bit's drilling speed, thrust, and drilling path based on real-time formation feedback and historical data. Compared with existing fixed-parameter tunneling methods, this adaptive adjustment improves the equipment's adaptability to different geological conditions, ensuring the stability and continuity of the drilling process. The deep neural network analyzes formation characteristics through a multilayer perceptron model and adjusts the drill bit's drilling parameters based on real-time formation feedback data.

[0126] The automatic chip removal module in this invention is designed with a spiral chip removal channel and an airflow auxiliary layer, which can efficiently remove chips during drilling, prevent chip accumulation and blockage of the channel, and ensure smooth chip removal. Compared with traditional chip removal systems, the chip removal efficiency of this invention is significantly improved, reducing the frequency of equipment downtime and maintenance caused by chip accumulation.

[0127] based on Figure 1 The intermittent auger shown is, for example Figure 2 As shown, this embodiment of the invention provides a control method for an intermittent auger tunneling machine. The control method includes steps S101-S104.

[0128] S101, Detect the tunneling parameters and control parameters of the auger drilling rig module.

[0129] In this embodiment, the tunneling parameters include formation resistance, rotational torque, vibration frequency, and vibration amplitude. Control parameters include thrust, rotational speed, and drilling path.

[0130] S102. Using the tunneling parameters as feedback, perform PI calculation on the control parameters to obtain the initial control parameters for the next cycle.

[0131] As one possible implementation, step S102 can be specifically implemented as steps S1021-S1022.

[0132] S1021. Determine the control error based on the tunneling parameters and control parameters.

[0133] S1022. Based on the control error, perform PI calculation to determine the initial control parameters for the next cycle.

[0134] S103. Based on the tunneling parameters, control parameters, initial control parameters, and preset optimization model, optimize the control parameters to obtain the target control parameters for the next cycle.

[0135] In this embodiment, the preset optimization model is obtained by training based on tunneling parameters and control parameters within a historical period.

[0136] As one possible implementation, step S103 can be specifically implemented as steps S1031-S1032.

[0137] S1031. Generate the tunneling vector based on the tunneling parameters, control parameters, and initial control parameters;

[0138] S1032. Based on the tunneling vector and the preset optimization model, determine the target control parameters for the next cycle.

[0139] S104. Based on the target control parameters, control the micro horizontal auger drilling rig module to perform tunneling.

[0140] As one possible implementation, step S104 can be specifically implemented as steps S1041-S1042.

[0141] S1041. Based on the drilling path in the target control parameters, determine the target area on the current tunneling face.

[0142] S1042, Control the micro horizontal auger drilling rig module to move to the target area.

[0143] S1043. Based on the thrust and rotation speed in the target control parameters, determine the target rotation speed and target thrust of the drill bit in the micro horizontal auger drilling rig module.

[0144] S1044. Control the running status of the drill bit in the micro horizontal auger drilling rig module to the target speed and target thrust.

[0145] S1045, Control the micro horizontal auger drilling module to advance.

[0146] This invention provides a control method for an intermittent auger tunneling machine. First, using tunneling parameters as feedback, a PI calculation is performed on the control parameters to obtain the initial control parameters for the next cycle. The method considers the influence of ground resistance, rotational torque, and vibration, ensuring that the initial control parameters adapt to the actual conditions of the current tunneling face. Then, this invention optimizes the initial control parameters using a preset optimization model. Since the preset optimization model is trained based on tunneling and control parameters from a historical period, it fully considers the actual control conditions during tunneling in that period, making the target control parameters more consistent with the actual conditions of the current tunneling face. This improves the control accuracy of the auger tunneling machine, achieves high-precision control, avoids drill bit deviation and torque instability problems, and improves the tunneling efficiency of the auger tunneling machine.

[0147] Optionally, the control method for the intermittent spiral tunneling machine provided in this embodiment of the invention further includes steps S201-S207 before step S103.

[0148] S201. Obtain the tunneling parameters and control parameters of the intermittent auger tunneling machine during historical periods.

[0149] S202. Divide the tunneling parameters and control parameters within the historical period into time windows to obtain tunneling parameters and control parameters for multiple cycles.

[0150] S203. Based on the tunneling parameters and control parameters of the first cycle, perform PI calculation to obtain the initial control parameters for the second cycle.

[0151] In some embodiments, the first period is any one of a plurality of periods, and the second period is the period following the first period.

[0152] S204. Based on the tunneling parameters and control parameters of the first cycle, and the initial control parameters of the second cycle, determine the tunneling vector of the first cycle.

[0153] S205. Based on the tunneling parameters of the second cycle, determine the target control parameters for the second cycle.

[0154] S206. Using the tunneling vector of each cycle in multiple cycles as input and the target control parameters of the next cycle as output, construct multiple training samples.

[0155] S207. Based on multiple training samples, perform neural network training to obtain a preset optimized model.

[0156] For example, step S207 can be specifically implemented as steps A1-A3.

[0157] A1. Based on multiple training samples, perform neural network training to obtain an initial model.

[0158] A2. Construct teacher-student models using the initial model as the teacher model and models with the same depth as the initial model as student models.

[0159] A3. Based on multiple training samples, knowledge distillation training is performed on the student model in the teacher-student model to obtain the preset optimized model.

[0160] Thus, this invention obtains a preset optimization model by training a neural network on historical data, which fully considers the actual control situation during the tunneling process in the historical period, making the target control parameters more consistent with the actual situation of the current tunneling face and improving the control accuracy of the auger tunneling machine.

[0161] Optionally, the control method for the intermittent spiral tunneling machine provided in this embodiment of the invention further includes steps S301-S303.

[0162] S301, Monitor the real-time friction coefficient of the micro horizontal auger drilling rig module.

[0163] S302. Based on the real-time friction coefficient and the preset friction coefficient range, determine the amount of lubricant injected.

[0164] S303. Control lubricant injection based on lubricant injection volume.

[0165] The lubrication and cooling module of this invention features a dual-loop cooling system, capable of independently cooling the auger bit and servo drive system to ensure that critical components operate within suitable temperature ranges. The lubrication unit automatically adjusts the lubricant injection volume based on real-time friction monitoring data, reducing friction loss and extending the service life of key components.

[0166] Optionally, the control method for the intermittent spiral tunneling machine provided in this embodiment of the invention further includes steps S401-S402.

[0167] S401. Determine the working condition of the intermittent auger tunneling machine based on the vibration frequency and vibration amplitude.

[0168] In some embodiments, the operating status includes normal operation or abnormal operation.

[0169] S402. If the intermittent spiral tunneling machine malfunctions, fault diagnosis is performed on the intermittent spiral tunneling machine based on the tunneling parameters and the preset support vector machine model to obtain the fault type.

[0170] In some embodiments, the fault types include excessive drill bit wear, abnormal torque, or excessive vibration.

[0171] This invention analyzes sensor data using Support Vector Machines (SVM), enabling timely alarms and automatic parameter adjustments when abnormal conditions such as drill bit wear, abnormal torque, or excessive vibration occur, preventing further escalation of the fault. This real-time anomaly detection and self-adjustment capability significantly reduces equipment maintenance costs and extends equipment lifespan.

[0172] For example, an embodiment of the present invention provides a method for operating an intermittent auger tunneling machine. The method includes steps S1-S8.

[0173] S1. Startup and Initial Setup

[0174] Control module for starting the intermittent spiral tunneling machine:

[0175] Before startup, operators first check if the system power supply is normal and ensure that the hardware and software of each module are properly connected. After the system starts, the control module begins to initialize each submodule, ensuring that the sensor monitoring module, servo electronic drive system, and adaptive control unit are in normal operating condition.

[0176] Check the system status and the connection status of each sensor:

[0177] The system performs a self-test, checking the status of each pressure sensor, torque sensor, and vibration sensor to ensure normal signal transmission between all sensors and the control module. If any connection fault is detected, the system will prompt the operator to check and repair it.

[0178] Set the initial drilling parameters via the control module:

[0179] Operators input initial drilling parameters, including drilling speed, thrust, and drilling path, through a human-machine interface (HMI). These parameters are preset based on current geological conditions and optimized using historical data, empirical models, and engineering standards. After receiving the input, the control module initializes the drill bit's motion control system to ensure the applicability of the initial parameters in actual operation.

[0180] S2, Drilling process monitoring

[0181] Start the miniature horizontal auger drilling rig module:

[0182] The operator presses the start button, and the servo-controlled drive unit begins to drive the auger drill bit to rotate and advance. The system collects the position and angle of the drill bit in real time and starts drilling based on the initial parameters.

[0183] The sensor monitoring module monitors the operating parameters during the drilling process in real time:

[0184] Once the sensor monitoring module is activated, pressure, torque, and vibration sensors begin real-time monitoring of key operating parameters during the drilling process. The system uses data feedback from these sensors to identify formation conditions, drill bit status, and equipment health.

[0185] Specific monitoring content:

[0186] Pressure sensor: Monitors the formation resistance experienced by the drill bit. Based on different geological conditions, the system adjusts the thrust in real time through sensor feedback data to ensure that the drill bit is not excessively obstructed or stuck by the formation.

[0187] Torque sensor: Monitors torque changes on the drive shaft to ensure the stability of the transmission system and prevent drive shaft breakage due to excessive torque.

[0188] Vibration sensors monitor the frequency and amplitude of vibrations during drilling to ensure a smooth drilling process. If the vibration frequency is abnormal, the system will issue a warning and take appropriate measures.

[0189] S3, Adaptive adjustment of the control module

[0190] Startup control module, including multi-parameter real-time control unit:

[0191] After the system starts up, the multi-parameter real-time control unit in the control module continuously analyzes the data fed back by the sensors, including parameters such as pressure, torque, and vibration. Based on this feedback, the system adjusts the drill bit's thrust, drilling speed, and drilling path in real time, enabling the equipment to maintain efficient and stable drilling under complex geological conditions.

[0192] The adaptive control unit is activated, and optimization is performed based on a deep neural network.

[0193] The adaptive control unit analyzes real-time formation characteristics and drilling status using a deep neural network (DNN) and automatically optimizes drilling parameters based on the model. This unit can dynamically adjust the thrust and rotation speed according to different geological conditions, ensuring the drill bit always operates in optimal condition.

[0194] The path planning unit uses reinforcement learning algorithms to optimize paths:

[0195] The path planning unit in the control module calculates the optimal drilling path using the Bellman equation through reinforcement learning algorithms. The system monitors obstacles (such as hard rock and cracks) in the drilling path in real time and automatically adjusts the path to avoid these obstacles, ensuring that the drill bit can smoothly pass through complex formations.

[0196] S4. Anomaly Detection and Handling

[0197] The anomaly detection unit analyzes sensor data using a support vector machine:

[0198] After the anomaly detection unit is activated, the Support Vector Machine (SVM) analyzes the real-time sensor data, including pressure, torque, and vibration data. Based on this data, the system diagnoses the equipment's operating status and detects any anomalies.

[0199] Detection and handling of abnormal operating states: The system can detect the following abnormal situations:

[0200] Excessive drill bit wear: When the vibration frequency or drill bit torque reported by the sensor is abnormal, the system determines that the drill bit may be worn.

[0201] Abnormal torque: When the torque sensor detects excessively high torque, it may indicate a problem with the drive shaft. The system will immediately adjust the torque output to prevent damage.

[0202] Excessive vibration: When the vibration sensor detects high-frequency vibration, the system determines that the drilling process is unstable and may need to reduce the drilling speed or adjust the drilling path.

[0203] When the above-mentioned anomalies are detected, the anomaly detection unit will automatically adjust the control parameters and send an alarm to the operator through the control module, reminding the operator to take further inspection or intervention measures.

[0204] S5, Automatic chip removal

[0205] The automatic chip removal module is activated, and the chips are discharged through the spiral chip removal unit:

[0206] After the automatic chip removal module is activated, the spiral chip removal unit works synchronously with the spiral drill bit, and the system discharges the chips generated during drilling through the chip removal channel. The chip removal process is synchronized with the drilling operation to ensure that drill chips around the drill bit do not clog the borehole.

[0207] The automatic cleaning unit activates the mechanical scraper and airflow auxiliary unit:

[0208] When debris accumulation is detected in the chip removal channel, the automatic cleaning unit is activated. Mechanical scrapers begin to physically clean the chip removal channel, removing the accumulated debris. Simultaneously, the airflow auxiliary unit activates high-pressure gas to blow fine debris out of the chip removal channel, ensuring that the channel remains unobstructed at all times.

[0209] S6, Lubrication and Cooling

[0210] The lubrication and cooling module is activated, and the cooling circuit unit begins operation:

[0211] The system activates the lubrication and cooling module, effectively cooling the auger bit and servo drive system through the cooling circuit unit. Coolant flows through the drill bit and transmission system via a dual-circuit system, ensuring the equipment's operating temperature remains within the set range and preventing overheating that could lead to wear or malfunction.

[0212] The lubrication unit is activated, and the lubricant injection volume is automatically adjusted.

[0213] Based on real-time feedback from the friction sensor, the lubrication unit automatically adjusts the amount of lubricant injected. The lubrication unit increases or decreases the lubricant injection as needed according to the system's friction status to ensure that the friction between the drill bit and the transmission system remains within a reasonable range, thus extending equipment life.

[0214] S7, Self-learning and Optimization

[0215] Initiate a self-learning unit to optimize based on real-time acquired historical drilling data:

[0216] The self-learning unit collects various data in real time during the drilling process and learns and optimizes drilling parameters under different geological conditions. This module gradually optimizes the parameter model based on the performance of the drill bit under different formation conditions, enabling the system to automatically select the best drilling parameters in subsequent operations.

[0217] The drilling strategy is gradually improved using deep neural networks:

[0218] The system's self-learning unit progressively improves the drilling strategy through a deep neural network. This algorithm optimizes drilling speed, thrust, and path planning based on historical data and real-time feedback, enhancing the system's performance under complex geological conditions.

[0219] S8, Stop and Close

[0220] After completing the scheduled drilling task, gradually reduce the drill bit speed and thrust:

[0221] When the predetermined drilling depth is reached or the drilling task is completed, the system will gradually reduce the drill bit's rotation speed and thrust to prevent sudden stops from causing equipment damage or material deformation. The control module will adjust the rotation speed based on real-time data to ensure a safe system shutdown.

[0222] Stop the operation of the sensor monitoring module and the lubrication and cooling module:

[0223] After the drill bit stops, the sensor monitoring module ceases real-time monitoring of operating parameters, and the lubrication and cooling modules also stop working. At this stage, the operator should perform a preliminary inspection of the equipment to ensure there are no abnormalities.

[0224] Shut down all modules and check for wear and tear on system components:

[0225] Finally, the operator shuts down all modules of the system and inspects and records the wear and tear of key components such as the drill bit, transmission system, and cooling system. The system automatically generates an operation report for the operator to use for subsequent maintenance.

[0226] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0227] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0228] Figure 3 A schematic diagram of the structure of a control module for an intermittent spiral tunneling machine according to an embodiment of the present invention is shown. The control module 500 includes a communication unit 501 and a processing unit 502.

[0229] The communication unit 501 is used to detect the tunneling parameters and control parameters of the auger drilling rig module. The tunneling parameters include formation resistance, rotational torque, vibration frequency, and vibration amplitude; the control parameters include thrust, rotational speed, and drilling path.

[0230] The processing unit 502 is used to perform PI calculation on the control parameters with the tunneling parameters as feedback to obtain the initial control parameters for the next cycle; based on the tunneling parameters, control parameters, initial control parameters, and a preset optimization model, it optimizes the control parameters to obtain the target control parameters for the next cycle. The preset optimization model is trained based on the tunneling parameters and control parameters in historical periods; based on the target control parameters, it controls the micro horizontal auger drilling rig module to perform tunneling.

[0231] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Figure 4 As shown, the electronic device 600 includes: a processor 601, a memory 602, and a computer program 603 stored in the memory 602 and executable on the processor 601. When the processor 601 executes the computer program 603, it implements the steps in the above-described method embodiments, for example... Figure 2 The steps S101-S104 are shown. Alternatively, when the processor 601 executes the computer program 603, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 3 The functions of the communication unit 501 and the processing unit 502 shown are illustrated.

[0232] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A control method for an intermittent screw tunneling machine, characterized in that, The intermittent spiral tunneling machine includes a micro horizontal spiral drilling rig module, a sensor module, and a control module; the method includes: The detection module includes the tunneling parameters and control parameters of the auger drilling rig. The tunneling parameters include ground resistance, rotational torque, vibration frequency, and vibration amplitude. The control parameters include thrust, rotational speed, and drilling path. Using the tunneling parameters as feedback, the control parameters are calculated using PI to obtain the initial control parameters for the next cycle; Based on the tunneling parameters, control parameters, and initial control parameters, as well as the preset optimization model, the control parameters are optimized to obtain the target control parameters for the next cycle. The preset optimization model is obtained by training based on the tunneling parameters and control parameters in historical periods. Based on the target control parameters, the micro horizontal auger drilling module is controlled to perform tunneling. Before optimizing the control parameters based on the tunneling parameters, control parameters, initial control parameters, and a preset optimization model to obtain the target control parameters for the next cycle, the method further includes: acquiring the tunneling parameters and control parameters of the intermittent spiral tunneling machine over a historical period; dividing the tunneling parameters and control parameters over a historical period into time windows to obtain tunneling parameters and control parameters for multiple cycles; performing PI calculation based on the tunneling parameters and control parameters of the first cycle to obtain the initial control parameters for the second cycle; the first cycle being any one of the multiple cycles, and the second cycle being the cycle following the first cycle; determining the tunneling vector for the first cycle based on the tunneling parameters and control parameters of the first cycle and the initial control parameters for the second cycle; determining the target control parameters for the second cycle based on the tunneling parameters of the second cycle; constructing multiple training samples using the tunneling vector of each cycle as input and the target control parameters of the next cycle as output; and training a neural network based on the multiple training samples to obtain the preset optimization model.

2. The control method for an intermittent spiral tunneling machine according to claim 1, characterized in that, The step of using the tunneling parameters as feedback to perform PI calculation on the control parameters to obtain the initial control parameters for the next cycle includes: Based on the tunneling parameters and the control parameters, the control error is determined; Based on the control error, PI calculation is performed to determine the initial control parameters for the next cycle.

3. The control method for an intermittent spiral tunneling machine according to claim 1, characterized in that, The step of optimizing the control parameters based on the tunneling parameters, control parameters, initial control parameters, and a preset optimization model to obtain the target control parameters for the next cycle includes: Based on the tunneling parameters, control parameters, and initial control parameters, a tunneling vector is generated; Based on the tunneling vector and the preset optimization model, the target control parameters for the next cycle are determined.

4. The control method for an intermittent spiral tunneling machine according to claim 1, characterized in that, The step of training a neural network based on the multiple training samples to obtain the preset optimized model includes: Based on the multiple training samples, neural network training is performed to obtain an initial model; Using the initial model as the teacher model and a model with the same depth as the initial model as the student model, construct a teacher-student model; Based on the multiple training samples, knowledge distillation training is performed on the student model in the teacher-student model to obtain the preset optimized model.

5. The control method for an intermittent spiral tunneling machine according to claim 1, characterized in that, The step of controlling the micro horizontal auger drilling rig module to excavate based on the target control parameters includes: Based on the drilling path in the target control parameters, the target area on the current tunnel face is determined; Control the miniature horizontal auger drilling rig module to move to the target area; Based on the thrust and rotation speed in the target control parameters, the target rotation speed and target thrust of the drill bit in the micro horizontal auger drilling rig module are determined. Control the operating state of the drill bit in the micro horizontal auger drilling module to the target rotational speed and target thrust; Control the micro horizontal auger drilling module to advance forward.

6. The control method for an intermittent spiral tunneling machine according to claim 1, characterized in that, The method further includes: Monitor the real-time friction coefficient of the miniature horizontal auger drilling module; Based on the real-time friction coefficient and the preset friction coefficient range, the lubricant injection amount is determined; Based on the lubricant injection volume, the lubricant injection is controlled.

7. The control method for an intermittent spiral tunneling machine according to claim 1, characterized in that, The method further includes: Based on the vibration frequency and vibration amplitude, the operating status of the intermittent auger is determined, including normal operation or abnormal operation. If the intermittent auger tunneling machine malfunctions, a fault diagnosis is performed on the intermittent auger tunneling machine based on the tunneling parameters and a preset support vector machine model to obtain the fault type, which includes excessive drill bit wear, abnormal torque, or excessive vibration.

8. A control module for an intermittent spiral tunneling machine, characterized in that, include: The communication unit is used to detect the tunneling parameters and control parameters of the auger drilling rig module. The tunneling parameters include ground resistance, rotational torque, vibration frequency, and vibration amplitude. The control parameters include thrust, rotational speed, and drilling path. The processing unit is used to perform PI calculation on the control parameters with the tunneling parameters as feedback to obtain the initial control parameters for the next cycle; Based on the tunneling parameters, control parameters, and initial control parameters, as well as the preset optimization model, the control parameters are optimized to obtain the target control parameters for the next cycle. The preset optimization model is trained based on the tunneling parameters and control parameters in historical periods. Based on the target control parameters, the micro horizontal auger drilling rig module is controlled to tunnel. The communication unit is also used to acquire the tunneling parameters and control parameters of the intermittent auger tunneling machine during historical periods; the processing unit is also used to divide the tunneling parameters and control parameters during historical periods into time windows to obtain the tunneling parameters and control parameters for multiple cycles; and to perform PI calculation based on the tunneling parameters and control parameters of the first cycle to obtain the initial control parameters for the second cycle. The first cycle is any one of the plurality of cycles, and the second cycle is the next cycle after the first cycle; based on the tunneling parameters and control parameters of the first cycle, and the initial control parameters of the second cycle, the tunneling vector of the first cycle is determined; based on the tunneling parameters of the second cycle, the target control parameters of the second cycle are determined. Multiple training samples are constructed by taking the tunneling vector of each cycle as input and the target control parameters of the next cycle as output. Based on the multiple training samples, a neural network is trained to obtain the preset optimized model.

9. An intermittent spiral tunneling machine, characterized in that, The intermittent spiral tunneling machine includes electronic equipment, which includes a memory and a processor. The memory stores a computer program, and the processor is used to call and run the computer program stored in the memory to perform the steps of the method as described in any one of claims 1 to 7.

Images