198 results about "Thrust control" patented technology

The invention provides a DLH-IHBA-based adaptive cycle engine control law optimization method, and belongs to the technical field of aero-engine control, and the method comprises the steps: building an adaptive cycle engine model, and determining an optimization variable based on the adaptive cycle engine model; according to the control mode of each self-adaptive cycle engine, constraint conditions and an objective function based on optimization variables are determined, the control modes comprise a steady state control mode and a transition state control mode, and the steady state control mode comprises a minimum fuel consumption control mode, a maximum thrust control mode and a minimum turbine front temperature control mode; and based on the objective function and the constraint condition, optimizing the control rule of each control mode by adopting a multi-dimensional learning prey strategy fused with a badger optimization algorithm to obtain an optimal control variable, and adopting Tent mapping as initial particle swarm position mapping. According to the scheme, the convergence speed of engine control rule optimization is increased, and the optimization effect and the engine performance are improved.

The invention relates to the technical field of unmanned aerial vehicle control, in particular to an unmanned aerial vehicle dynamic obstacle avoidance method based on multi-sensor fusion. Comprising the steps of receiving an image sequence, a depth point cloud set, a pose state parameter and a flight speed parameter; calculating an illumination distortion gradient value and a speckle noise entropy value based on the image sequence and the depth point cloud set; performing coordinate registration and feature extraction on the image sequence, the depth point cloud set and the pose state parameter, and outputting a visual feature set and a radar feature set; generating a weighted visual feature set and a weighted radar feature set through a weight adjustment function, and generating a joint heterogeneous feature tensor through alignment splicing; and generating a body attitude and thrust control instruction by using the combined heterogeneous feature tensor through a probability prediction model and a model prediction control algorithm device. According to the method, through cross-domain multiplexing and deep coupling of the body physical parameters in the data stream, error accumulation and decision delay caused by multi-stage series calculation are avoided, and global performability of an obstacle avoidance task is facilitated.

The invention discloses an intelligent control method and system for dynamic balance of three floating bodies for crude oil transfer in deep and far sea. The method comprises the following steps: (1) data acquisition and state vector construction; (2) constructing a dynamic response prediction model: constructing a floating body historical motion database based on the initial motion data set, fusing hydrodynamic interference coefficient matrix calculation and multi-body motion mixed constraint analysis, and designing a space-time prediction algorithm based on a graph neural network and a recurrent nerve process to obtain a dynamic response prediction model; establishing a dynamic response prediction model under close-range coupling interference of the three floating bodies; (3) evaluating and correcting data confidence; (4) self-adaptive thrust control and early warning are carried out; and (5) visual monitoring and log management. The problems that in the prior art, positioning precision is low, response lags behind, the abnormal rate of sensor data is high, hydrodynamic coupling interference is not fully considered, and visual monitoring and intelligent early warning are lacked are solved, and the safety, stability and operation efficiency of the deep and far sea crude oil transfer process are effectively improved.

The invention relates to the technical field of robot and unmanned aerial vehicle control, and solves the technical problems that in the prior art, when an unmanned aerial vehicle platform carries a mechanical arm for operation, the total center of mass of a system drastically shifts due to movement of the mechanical arm, then dynamically changing disturbance torque is generated, and the attitude of an unmanned aerial vehicle is unstable and even out of control. The coupling dynamics compensation and vibration suppression method for the aerial work platform comprises the steps that feedforward compensation torque used for counteracting disturbance torque generated due to the change of the position of the total mass center is obtained and decoupled into a control instruction for controlling thrust of multiple rotor wings of an unmanned aerial vehicle platform through a mixed control matrix, and accurate control of the unmanned aerial vehicle platform is realized. According to the method, the self-adaptive feed-forward compensation mechanism is introduced, the mass center change caused by movement of the mechanical arm can be sensed and predicted in real time, the feed-forward compensation torque is generated accordingly, the disturbance torque generated accordingly is actively counteracted, and therefore the attitude stability and operation precision of an unmanned aerial vehicle platform are remarkably improved.

The invention provides a rotor unmanned aerial vehicle bidirectional thrust control method and device based on deep reinforcement learning, and the method comprises the steps: S01, constructing an unmanned aerial vehicle bidirectional thrust dynamics model which comprises an unmanned aerial vehicle dynamics model and a motor-blade model for achieving the bidirectional thrust control; s02, using a deep reinforcement learning model to construct a neural network controller for controlling the action of the unmanned aerial vehicle based on the unmanned aerial vehicle bidirectional thrust dynamical model, the input of the neural network controller being the difference between the current state and the target state of the unmanned aerial vehicle, and the output being the expected thrust of each motor of the unmanned aerial vehicle; and step S03, training the neural network controller, and using the trained neural network controller to control the unmanned aerial vehicle, so that the unmanned aerial vehicle stably hovers to a target state. The method has the advantages of being high in control precision, good in stability and high in adaptability, and stable hovering of the unmanned aerial vehicle in severe states such as a large posture, a large speed and a large angular speed is achieved.

The invention provides a fire-fighting unmanned aerial vehicle attitude control system and a control method thereof, and relates to the technical field of fire-fighting unmanned aerial vehicle attitude control. A sensing terminal, a measuring terminal, a lateral rotor wing and a control terminal are arranged on the unmanned aerial vehicle; determining a target spraying position of the fire extinguishing medium based on the sensing terminal; the medium flow of a fire extinguishing medium in the fire gun and the heat convection vector force in the environment horizontal plane are measured based on the measuring terminal; reverse thrust is provided in the spraying direction of the fire extinguishing medium based on the lateral rotor wings; the control terminal determines the current muzzle position of the fire gun on the horizontal plane according to the medium flow and the heat convection vector force; determining the spraying position deviation of the fire gun according to the current muzzle position and the target spraying position; and the magnitude and direction of reverse thrust provided by the lateral rotor wings are controlled according to the jetting position deviation, so that the muzzle position of the fire gun when the fire gun executes a fire extinguishing task is corrected. The fire extinguishing efficiency of a fire scene and the completion quality of a fire extinguishing task are improved.

The invention relates to a buoy observation data automatic comparison and maintenance method, which comprises the following steps: fusing buoy real-time position data and ocean current prediction data according to an ocean current change trend, and calculating a buoy position deviation value; if the position deviation value exceeds a preset threshold value, high-precision real-time position data are obtained through sensor calibration, and thrust control parameters are generated through an optimization algorithm; obtaining buoy state data through structural integrity detection, adjusting the position of the buoy to a target area based on the thrust control parameters, and judging whether the position deviation meets the requirement or not; energy consumption data of the propulsion device are obtained, an energy consumption curve is extracted from a pre-established energy consumption model, and an optimization algorithm is adopted to generate energy consumption parameters; adjusting the working mode of the propulsion device according to the energy consumption parameter, and judging whether the residual capacity of the battery meets operation requirements; and if the battery capacity is lower than the preset threshold value, switching to a low-power-consumption mode, and adjusting the data acquisition frequency of the sensor by adopting a machine learning algorithm to obtain a data acquisition scheme.

The invention discloses a hydraulic control system of an excavator and the excavator. The hydraulic control system comprises a hydraulic pump, a supporting leg device, a working device and a controller. The working device comprises a working hydraulic valve group, the supporting leg device comprises a supporting leg frame valve group and a supporting leg claw, and the controller is connected with the control end of the working hydraulic valve group and the control end of the supporting leg frame valve group; the controller outputs a first signal to the working hydraulic valve group, and the bucket is inserted into the ground; a second signal is output to the working hydraulic valve group, and the working device provides upward boosting force along the slope surface; the controller outputs a third signal to a supporting leg frame valve group, and a supporting leg claw is lifted; a fourth signal is output to a supporting leg frame valve group, and a supporting leg claw presses the ground downwards; in a single working cycle of slope climbing, a first signal, a third signal, a second signal and a fourth signal are output in sequence; and after the excavator arrives at the target operation site and the controller outputs a fourth signal, slope-holding excavation operation is carried out. According to the invention, climbing and hill-holding operation of ramps with the gradient of less than 35 degrees can be realized.

The invention relates to a power transmission network overhead line inspection device based on a miniaturized unmanned airship, and belongs to the field of power inspection. The objective of the invention is to solve the problem that long-distance, high-precision, safe and stable power transmission line automatic inspection cannot be realized under complex terrain and severe weather conditions due to short cruising ability of an existing power inspection unmanned aerial vehicle and low intelligent level and poor environmental adaptability of a traditional unmanned airship. The airship main body adopts a light high-strength sandwich structure flexible airship body, and a thin film solar cell is integrated on the surface of the airship main body to prolong the endurance; the intelligent control module fuses an environment sensing unit and a path planning unit, and realizes intelligent obstacle avoidance and dynamic path planning based on a sensor group and a danger sensing model; the vector power system is provided with three power sources of a right-angle fan structure, and the three power sources are arranged at the tail, the top and the bottom of the boat respectively and provide omni-directional vector thrust control. The buoyancy adjusting system dynamically adjusts the buoyancy through the symmetrical inflatable sub-cabins, so that the wind resistance stability and the terrain adaptability are enhanced.

The invention discloses a wind-light wave hybrid drive unmanned ship which comprises a ship body, a sail propelling device, a propeller propelling device, a wave drive device, a solar power supply system and a control module. A solar panel is installed on the ship body and can convert solar energy into electric energy to be stored in a battery. The sail propelling device provides main propelling force for the unmanned ship by means of wind energy; the wave driving device generates propulsive force by utilizing wave energy and has a course control function; the propeller propelling device serves as auxiliary power and provides thrust under specific working conditions. The control module intelligently regulates and controls the working modes of the propelling devices according to the sea condition information based on a reinforcement learning energy management algorithm, and multi-energy cooperative driving is achieved; the unmanned ship solves the problems of single energy dependence, insufficient navigational speed and maneuverability and tedious deployment and recovery of the existing unmanned ship, has the advantages of long endurance, high maneuverability, environmental protection and easy operation, and is suitable for various tasks of ocean observation, scientific research monitoring and military reconnaissance.

The invention discloses a thruster thrust control method for underwater robot driving. Comprising the following steps: firstly, constructing an extended state observer and a direct adaptive robust controller of the underwater propeller; then, the real-time state of the underwater propeller is obtained, the expansion state observer carries out expansion state observation according to the real-time state of the underwater propeller and then outputs an external interference compensation value, and the direct self-adaptive robust controller outputs the expected torque of the underwater propeller according to the real-time state of the underwater propeller and the external interference compensation value; and then propeller nonlinear compensation is carried out, actual current is obtained, and the underwater propeller is controlled by using the actual current. According to the method, the thrust of the underwater propeller can be controlled in real time, and the problems of incomplete model hydrodynamic characteristic description, uncompensated dead zone characteristics and inaccurate disturbance estimation under the actual working condition of the underwater propeller are solved, so that the thrust control error of the propeller is reduced, the system stability is ensured, and the control performance is improved.

The present application relates to the technical field of unmanned aerial vehicle intelligent control, and particularly relates to a method and system for analyzing the power of an unmanned aerial vehicle engine based on self-adaptive working conditions. The method comprises the following steps: obtaining flight task data; extracting task behavior according to the flight task data to obtain task behavior data; mapping working conditions according to the task behavior data to obtain working condition data; extracting features from the working condition data to obtain working condition feature data; identifying working condition discontinuity according to the working condition feature data to obtain working condition discontinuity data; and re-estimating the power demand of a sudden working condition according to the working condition discontinuity data to obtain sudden working condition power demand data. Through working condition identification and dynamic power re-estimation driven by task behavior, the present application can adaptively respond to load fluctuations and sudden disturbances in dynamic flight tasks of unmanned aerial vehicles, and achieve engine thrust control and energy consumption optimization.

The application discloses a kind of high-speed low-energy consumption autonomous control method of underwater vehicle based on prediction model optimization, belongs to underwater vehicle autonomous control technical field.The application establishes the longitudinal prediction model of vehicle, in each control cycle, with current navigation state as initial condition, based on the prediction model is carried out rolling optimization.Optimization function not only includes depth tracking error, more critically, introduce the navigation resistance estimation term directly related with angle of attack and rudder angle, to minimize total resistance as target, solve the optimal angle of attack sequence in future time domain and corresponding rudder angle, thrust control instruction.The application embeds hydrodynamic optimization in real-time closed-loop control, so that the vehicle can actively maintain the optimal drag-reducing attitude navigation, rather than passive maintenance level, thereby significantly reducing the total resistance and energy consumption of underwater vehicle high-speed navigation, effectively suppresses the phenomenon of buried bow, improves navigation stability.

The present invention relates to a method and system for rapid thrust response control of an aero-engine based on redundant actuators, and belongs to the field of aero-engines. The method comprises the following steps: constructing a transfer function for controlling thrust based on the main fuel flow rate and the tail nozzle throat area; calculating the transfer functions of the three modules for controlling thrust based on the main fuel flow rate and the tail nozzle throat area; solving the transfer functions for controlling thrust based on the main fuel flow rate and the tail nozzle throat area, and designing a valve position control (VPC) controller based on the transfer function L, thereby achieving rapid thrust response control. While increasing the thrust control bandwidth, the present invention avoids the problems of turbine inlet temperature exceeding the limit and compressor surge caused by the high bandwidth under traditional single-variable control.

The invention provides a non-singular semi-analytical method for forecasting a low-thrust perturbation orbit. The method comprises the following steps: firstly, establishing a Gaussian variational equation for describing spring equinox orbital element evolution under small thrust control based on a periodic small thrust hypothesis; thirdly, constructing a long-term equation and a short-period term based on the average spring equinox orbital elements, performing large-step integration on the long-term equation to obtain a flat root, and then performing orbital element correction through the short-period term to finish high-precision orbital forecasting; and finally, establishing an analytic form error estimation model through a semi-major-axis second-order long-term equation, and using the analytic form error estimation model to evaluate orbit forecast errors. The semi-analytic low-thrust orbit forecasting method provided by the invention achieves good balance between calculation efficiency and precision, avoids the problem of singularity, and is suitable for high-precision forecasting of any low-thrust elliptical orbit; the error estimation model provided by the invention can effectively quantify the prediction error and enhance the reliability of the orbit prediction results of most small eccentricity rate on-orbit satellites.

The present invention comprises a system which includes a novel quick release thruster mount system using one or more removable elements allowing the thrusters to be removed quickly. The present invention also comprises a novel “float compartment centric” design where no wiring to the cockpit is necessary. Redundant power units are self-contained and protected. The novel design incorporates thrust force over the surface of the water rudders improving directional control. The rudder anti lift device ALPB allows the rudders to remain in the water while reverse or braking thrust is applied. Control and monitoring are done wirelessly from the safety of the cockpit reducing hazard while maneuvering to avoid prop strike hazards to pilot, persons or objects. The system offers the ability to maintain positive directional control while taxing downwind resisting the inherent weathervane forces, braking, and turning maneuvers unachievable with current methods. The system differs from any prior art due to the aft location of drive components, method for deployment, and the fact that the drive system does not mount directly to the float itself but rather the water rudders. These forces are marginal in comparison to what is needed when one takes into consideration the Moment and Arm location of the force and the smaller lightweight thrusters do more work with less effort.

This invention discloses a radioactive particle strip implantation system and method, relating to the field of medical device technology. It includes: an implantation gun and a particle strip module; the implantation gun includes: a gun body; a drive assembly disposed within the gun body, including a driver and a thrust control unit; a push rod, drively connected to the power output end of the driver; a particle strip placement slot disposed at the front end of the gun body for placing the particle strip module, and coaxially arranged with the push assembly; the gun body has a docking part at the front end of the particle strip module compartment for connecting an implantation needle; the push rod can pass through the particle strip module to push the particle strip into the implantation needle; the particle strip module includes: a module body; multiple radioactive particles and multiple hemostatic drug units are pre-sealed in an alternating arrangement within the module body; the radioactive particles and hemostatic drug units are coaxially arranged and can be pushed into the implantation needle by the push rod. This invention uses a pre-assembled plate stacking structure to make the spacing of the radioactive particles adjustable, simplifying on-site operation.

The application discloses a combustion chamber thrust control method in the acceleration process of a scramjet engine, and adopts a gradually expanding series connection cavity combustion chamber, fuel injection holes are arranged on the upstream of two cavities, the first cavity is a pre-combustion zone, and the second cavity is a main combustion zone; the thrust control method is as follows: when the combustion chamber inlet Mach number is low, the combustion mode of the pre-combustion zone is controlled to be kept in a weak subsonic combustion mode, and the combustion mode of the main combustion zone is controlled to be kept in a strong subsonic combustion mode; when the combustion chamber inlet Mach number is high, the combustion mode of the pre-combustion zone is controlled to be kept in a supersonic combustion mode, and the combustion mode of the main combustion zone is controlled to be kept in a strong subsonic combustion mode. The application is applied to the field of scramjet engines, can guarantee that the combustion chamber can generate higher thrust in a wide flight Mach number range, simultaneously avoids thermal choking, and the thrust mutation caused by combustion mode conversion is smaller, thrust control is more stable, and smooth transition of thrust during combustion mode conversion can be realized.

The present invention discloses an intelligent direct thrust control method for a turbofan engine based on reinforcement learning, comprising the following steps: Step 1), select the structures and parameters of the policy and evaluation networks, and design the form of the direct thrust controller considering the protection of key safety parameters and the form of the reward of the reinforcement learning environment; Step 2), based on the continuous policy gradient reinforcement learning algorithm, use the component-level model to build an environment for exploration, and train the intelligent agent policy network and evaluation network through the experience obtained from the exploration; Step 3), test the control performance of the intelligent agent within the full envelope range, and optimize the network structure and parameters. The present invention solves the problems of poor dynamic performance, high conservatism, and inaccurate thrust control in the indirect thrust control of turbofan engines. Through the reward designed by the present invention, the intelligent agent is motivated to search for the direct thrust controller with the optimal dynamic performance within the full envelope range, and it is ensured that the key safety parameters of the engine do not exceed the limit during the control process.

A jet propulsion boat includes: a boat body; a propulsion device that imparts propulsion force to the boat body to propel the boat body; an engine and an electric motor that drive the propulsion device; and a control device that determines which of an engine mode and an electric mode is to be used as an operation mode of driving the propulsion device in accordance with a condition, the engine mode configured to drive the propulsion device with the engine and the electric mode configured to drive the propulsion device with the electric motor while stopping the engine, and controls the engine and the electric motor to drive the propulsion device in the determined operation mode.

This application belongs to the field of robotics technology, providing a modular pipeline inspection robot and its control method suitable for pressurized water-filled pipe networks. It includes a head-mounted vision acquisition mechanism, a magnetic flux leakage (MF) detection mechanism, and a propulsion mechanism. The head-mounted vision acquisition mechanism acquires images of the inner surface of the pipe and is rotatably and sealingly connected to the MF detection mechanism. The MF detection mechanism includes a folding mechanism and a MF detection sensor. The folding mechanism is configured to be driven to control the MF detection sensor to be in contact with or away from the inner surface of the pipe. The MF detection sensor is used to acquire pipeline defect data. The MF detection mechanism is rotatably and sealingly connected to the tail-mounted main propeller. The control motherboard adjusts the thrust of each vertical propeller in real time through closed-loop control, controlling the robot to travel along the centerline of the pipe. This robot has a compact structure, flexible movement, can adapt to water-filled and certain pressure environments, and integrates multiple detection methods, improving the reliability and applicability of pipeline inspection.

An aircraft may include a tail having a rudder and a pair of wings. The pair of wings may include at least one flap and at least one roll control device. The aircraft may also include at least two thrust-producing devices. The aircraft may also include a differential thrust control system including a computing device having at least one processor. The at least one processer may be configured to control an attitude of the aircraft by selectively operating the at least two thrust-producing devices, the rudder, and the at least one roll control device based at least in part on a plurality of conditions provided by a plurality of sensors on the aircraft and a selected mode setting of a mode control panel. The computing device may be communicatively coupled to the at least two thrust-producing devices, the rudder, and the at least one roll control device.

The invention provides a cold air thruster of a microsatellite. The cold air thruster is integrated with a valve assembly, a piezoelectric actuator, an elastic mechanism, a capacitance displacement sensor, a flow sensor and a control unit. The valve assembly is driven by the executing mechanism, the gap between the disc-shaped diaphragm and the valve port is accurately regulated and controlled, and fine adjustment of gas flow and thrust is achieved. And the piezoelectric ceramic and elastic design of the actuating mechanism ensures that the valve is normally opened and quickly responded. The sensor system optimizes the control accuracy through feedback of a capacitance sensor and a flow sensor. The double-closed-loop control strategy adjusts driving voltage based on displacement and flow information, improves dynamic response and reduces control noise. The shell assembly provides comprehensive protection. The problems that in the prior art, thrust control precision is low, dynamic response performance is poor, and control noise is large can be effectively solved.

The present invention discloses a shaft multi-cylinder propulsion control system and its control method, belonging to the technical field of shaft boring machine equipment. The shaft multi-cylinder propulsion control system includes a hydraulic power source unit, multiple groups of propulsion cylinder units and a control valve group. The control valve group is provided with an electro-hydraulic proportional control valve group, which forms a closed-loop position servo control in cooperation with displacement detection elements supporting the propulsion cylinders, so as to achieve high-precision synchronous operation of multiple groups of propulsion cylinders. An independent electro-proportional pressure regulating unit is provided in each branch corresponding to the propulsion cylinders to achieve integrated control of flow regulation and independent pressure regulation. The control method includes a synchronous control step and an integrated control step, which completely cover all working conditions of shaft construction. The present invention effectively solves the problems of low synchronous accuracy, easy jamming, inaccurate boring thrust control and insufficient safety protection in the existing shaft propulsion system, and simultaneously takes into account high-precision control, wide-range speed regulation, constant-force boring and high safety protection, adapts to various shaft construction scenarios, and has high engineering application value.

The invention discloses an aero-engine direct thrust control method based on migration enhancement near-end strategy optimization, and belongs to the field of control algorithm design. Firstly, a thrust estimator based on a long and short term memory neural network is designed, training is carried out on a data set constructed by random actions, accurate estimation of thrust in a flight envelope is achieved, features extracted by the thrust estimator are optimized and trained on the basis of a near-end strategy, and the thrust in the flight envelope is accurately estimated. And finally, experimental verification is carried out, it is proved that the method can meet the real-time requirement of aero-engine control, and the training stability of the method is superior to that of a common reinforcement learning method.

The invention discloses a free piston generator system dead point control method and system based on energy balance, and relates to the technical field of piston generators. Establishing an energy balance equation by analyzing energy conversion and transfer in the system operation process; designing a stop point prediction model of the system based on the energy balance equation, and predicting a stop point position which can be reached in the current operation period; and a dead point error is obtained according to the predicted dead point position and the reference dead point position, and the motor thrust is updated through the dead point error, so that dead point control of the system is realized. A cascade system is established, an inner loop control system is a current loop, and an outer loop control system is a stop point position loop; according to the method, the motor thrust is updated in real time, dynamic correction of the stop point prediction model is combined, the interference suppression capability of the system and the control precision of the stop point position are remarkably improved, and the defect that traditional thrust control is insufficient in anti-interference performance is overcome.

Generally disclosed are rotor thrust balancing systems for turbomachinery and methods of using the same. For example, a rotor thrust balancing system for turbomachinery, where the turbomachinery defines a centerline extending a length of the turbomachinery. The system includes a rotating drive shaft, a thrust bearing, and a first waveguide sensor. The rotating drive shaft couples a turbine section and a compressor section of the turbomachinery. The thrust bearing supports the rotating drive shaft of the turbomachinery. The thrust bearing includes a plurality of ball bearings, an inner race coupled to the rotating drive shaft, and an outer race coupled to a fixed structure. The first waveguide sensor is coupled to the outer race at a first end of the waveguide sensor. The waveguide sensor transmits a vibration frequency from the thrust bearing to a second end of the waveguide sensor.

The invention provides a variable cycle engine control rule optimization method based on an improved seat head whale migration algorithm, and belongs to the technical field of engine control, and the method comprises the steps: building a variable cycle engine model, and determining an optimization variable; according to the control mode of each variable cycle engine, constraint conditions and an objective function are determined, the control modes comprise a steady state control mode and a transition state control mode, and the steady state control mode comprises a minimum fuel consumption control mode, a maximum thrust control mode and a minimum turbine front temperature control mode; and based on the target function and the constraint condition, an improved whale migration algorithm is adopted to optimize each control mode to obtain an optimal control variable, and the improved whale migration algorithm comprises the steps of taking Tent mapping as initial migration whale group position mapping and fusing a multi-dimensional learning hunting strategy. According to the processing scheme, the convergence speed and the optimization effect of the engine control rule optimization method are improved, and the engine performance is improved.

The application provides a shield tunneling model test tunnel mouth and main shaft sealing system and a verification method, effectively solves the problem that the influence of underground water on the test cannot be considered in the simulation test link of the prior art; the technical solution is that the application comprises a tunnel mouth sealing system and a main shaft sealing system; the tunnel mouth sealing system is composed of a first anti-fouling ring, a first sliding bearing, a first main seal, a first auxiliary sealing ring, a dustproof ring and a first static sealing ring, wherein the tunnel mouth sealing system is arranged on a tunnel mouth connecting piece and connected with a pressure container; the main shaft sealing system is composed of a second anti-fouling ring, a second sliding bearing, a second main seal, a second auxiliary sealing ring and a second static sealing ring; the application can accurately reproduce the tunneling process such as shield cutter disc rotation and shield advancement under high water pressure, and can provide more reference value test data for the optimization of shield construction parameters such as cutter disc rotating speed, thrust control and sealing structure design improvement of deep buried cross-sea and cross-river tunnels.