1819 results about "Simulation system" patented technology

The invention discloses a reservoir real-time scheduling simulation system based on a deep learning algorithm, and belongs to the technical field of intelligent water conservancy and artificial intelligence. Aiming at the problems of low prediction precision, poor multi-target coordination capability, weak coping uncertainty and the like of a traditional scheduling system, the system is designed to acquire hydrological, meteorological, water quality and engineering safety data through a multi-source data acquisition unit, and a multi-dimensional feature tensor is generated after preprocessing and fusion; the dispatching center server adopts an STGCN-LSTM mixed model to achieve high-precision prediction and uncertainty quantification of the water inflow process in the future 7-30 days, a reservoir hydrodynamic model and an MO-PPO algorithm are combined to complete multi-scene simulation and multi-target optimization decision, and an AF-DT mechanism dynamically adjusts the dispatching rule priority. According to the system, a sensing-decision-execution-feedback closed loop is constructed, the scheduling adaptive capacity and robustness are improved, the synergistic interaction of flood control, water supply, power generation and ecological protection is realized, and the system is suitable for real-time intelligent scheduling of large and medium reservoirs.

A crop growth modeling system includes a memory configured to store computer-readable instructions. The instructions cause to the system to use a digital twin component configured to create and manage a digital twin of a farm. The instructions cause to the system to use a data input component configured to receive data related to a defined set of land characteristics and environmental attributes for the farm. The instructions cause to the system to use a processing component configured to integrate the received data with the digital twin and to simulate at least one crop growth scenario based on the integrated data. The instructions cause to the system to use a prediction component configured to determine a predicted crop growth rate for the farm based on the simulations conducted by the processing component.

The invention relates to the technical field of coast engineering, in particular to an estuary sandy coast erosion and deposition simulation system based on the coupling effect of flood peak runoff, waves and tide, which comprises a training data generation module, an intelligent agent model construction module, a dynamic prediction engine module and a scene evaluation module. The training data generation module is used for outputting a hydrodynamic state field, a wave characteristic field, a bed surface shear stress field and a bed surface elevation variable quantity by utilizing a traditional numerical model to construct a training data set; the intelligent agent model building module is based on a deep learning network and introduces physical constraint loss function training to obtain an intelligent agent model; the dynamic prediction engine module loads the trained deep learning network to realize bed surface elevation variation prediction and update terrain boundary conditions; and the scene evaluation module executes erosion and deposition evolution simulation according to different hydrological boundary condition combinations and extracts terrain evolution data to quantitatively evaluate the coast stability and the channel deposition risk. The invention relates to the field of estuary dynamic landform simulation and coast engineering.

The invention discloses an intelligent simulation system and method based on a power distribution digital system, and relates to the technical field of power distribution network intelligent simulation. The event triggering module is used for constructing a composite triggering condition and obtaining an operation event based on the power distribution network data and the composite triggering condition; the event classification module is used for constructing an event template library and obtaining a target event type based on the running event and the event template library; the event-modeling demand mapping module is used for constructing an association rule base and obtaining a scene structure body and a modeling task package based on the association rule base and the target event type; and the modeling module is used for constructing a simulation model based on the modeling task package and the scene structure body, and obtaining an execution result based on the simulation model, so that the problem that the intelligence degree of event perception and response of the current dynamic modeling system of the power distribution network is insufficient is solved.

The invention is applicable to the technical field of coal bed gas development and geological sequestration, and provides a THMC multi-field coupling simulation method and system for a process of displacing CH4 by coal bed CO2, and the method comprises the following steps: collecting multi-source parameter information of a target coal bed; according to the multi-source parameter information, constructing a coal seam structure model comprising a matrix and a crack system; constructing a control equation system based on the coal seam structure model, and introducing a multi-field coupling mechanism to obtain a fully-coupled mathematical model; performing numerical solution on the fully-coupled mathematical model to obtain a spatio-temporal evolution result of the key field variables; and according to the spatio-temporal evolution result of the key field variable, evaluating the index of the target coal seam. According to the invention, a heat-force-gas-chemical multi-physical field full-coupling simulation system is constructed, so that the CH4 recovery rate and the CO2 storage stability can be accurately predicted. The method is suitable for gas injection-storage coupling optimization of a multi-coal-rank and low-permeability coal seam, and has high precision, high adaptability and remarkable engineering guidance value.

Techniques for generating simulations to evaluate a performance of an object controller. The controller may be configured to control one or more functionalities of a simulated object (e.g., a “smart object”) in a simulation, such as make the smart object operate like a human in a given scenario. A simulation system may generate one or more simulations based on log data captured by a vehicle operating in a physical environment. The simulation system may cause the object controller to control at least one smart object in the simulation, the smart object being representative of an actual object detected in the physical environment. The simulation system may compare a smart object trajectory to an actual object trajectory of the object to determine a performance metric associated with the object controller. Based on a determination that the performance metric satisfies a threshold, the simulation system may validate the object controller.

The invention belongs to the technical field of analog simulation, and particularly relates to an intelligent simulation system with an autonomous decision-making capability, which comprises simulation management used for task scene initialization, system parameter configuration and simulation process control and operation. The display system is used for 2D / 3D visual display and playback of simulation results; the model implementation system is connected with the simulation management and display system and is used for implementing a target model and a flight mode model according to configuration parameters; the intelligent target generation system is used for automatically generating a maneuvering combination strategy, a task load control strategy and a radar control strategy according to the simulation situation information generated by the model implementation system, and feeding back the maneuvering combination strategy, the task load control strategy and the radar control strategy to the model implementation system to drive simulation deduction; wherein the system can execute a plurality of simulation modes including large sample space random task simulation, task simulation without autonomous capability level and task simulation with certain autonomous capability level according to simulation types set by the simulation management and display system.

The invention provides experimental equipment and method for simulating filling and sealing of carbon dioxide in a goaf, and the experimental equipment comprises a simulation system, a slurry injection system, a gas injection system, a data acquisition and processing module, a recording, analyzing and displaying module and a data acquisition system. A simulated overlying strata of the simulation system naturally collapses to form a porous medium space model, slurry and carbon dioxide are injected into the porous medium space model through the slurry injection system and the gas injection system, and data acquisition is conducted on the curing process of the carbon dioxide through the data acquisition system; and the data is transmitted to the recording, analyzing and displaying module through the data collecting and processing module. According to the invention, the influence of carbon dioxide on the slurry solidification behavior and the solidification reaction penetration depth can be comprehensively researched, and a scientific basis is provided for optimizing material selection, proportion design and injection process parameters in practical engineering.

The invention provides a dynamic visual simulation system and method for carbon dioxide formation water reaction precipitation, and belongs to the technical field of geological sequestration. The dynamic visual simulation system and method for the carbon dioxide formation water reaction precipitation comprise a microcosmic etching chip model; a piston container; the pressure-making injection system is connected with the piston container; a carbon dioxide liquefaction module; the carbon dioxide quantitative injection system is connected with the carbon dioxide liquefaction module; the supercritical generator is connected to the downstream of the carbon dioxide quantitative injection system; a microscopic etching chip model is arranged in the visual reaction kettle, and the visual reaction kettle is connected with the supercritical generator; the back pressure loading system is connected to the outlet end of the visual reaction kettle; the microscopic image visual acquisition module is arranged above the visual reaction kettle; an annular pressure tracking pump; the control terminal computer is connected with all the modules, and the problems that the influence rule of sediment on reservoir seepage in carbon dioxide geological sequestration is unclear, and sequestration risks are difficult to predict are solved.

The invention discloses a mechanical arm simulation system supporting industrial quality inspection, which relates to the technical field of industrial automation and comprises a multi-physics field simulation engine module, a digital twin interface module, a defect sample library module and a cooperative control module. According to the method, traditional entity mechanical arm debugging is replaced by rigid body dynamics simulation based on a physical engine, loss and production line shutdown caused by repeated trial and error of equipment are avoided, rapid construction of the digital twin environment of the production line is achieved by means of an efficient CAD model conversion process and a lightweight loading technology, and high-fidelity optical simulation is achieved through a parameterized defect model library and high-fidelity optical simulation. Various common industrial defects and complex optical effects are covered, the modeling bottleneck of a quality inspection scene is broken through, real-time closed-loop interaction of visual inspection and motion control is realized by using thread separation and an efficient communication technology, and the recognition robustness of a visual algorithm to tiny defects is guaranteed; the reliability of algorithm verification is improved through the quantitative output of algorithm performance indexes and the comprehensive test of extreme working conditions by the simulation system.

The invention discloses a spare power automatic switching device test switch simulation test system, and belongs to the technical field of power grid simulation test. Probability distribution generated through kernel density estimation covers a fault scene of a 99% confidence interval, and the characterization capability of an extreme scene is enhanced; the time delay precision of a switch action sequence is controlled timely and reliably by combining the global search capability of quantum annealing and the local fine tuning of the particle swarm algorithm, and equipment damage caused by time sequence dislocation is avoided by combining the UWB technology and the phase compensation algorithm; through an objective function weight coefficient and a closed-loop feedback mechanism, an optimization objective can be dynamically adjusted according to a fault type, through real-time comparison of a physical device and digital twinning and through logic criterion goodness of fit analysis, control logic consistency can be guaranteed, and through loop response time difference analysis and two-dimensional index quantification, verification precision can be guaranteed. And the strict requirements of the power system on correct logic and quick action of the spare power automatic switching device are met.

The invention discloses a hydraulic engineering scheduling simulation system based on digital twinning, and relates to the technical field of hydraulic engineering scheduling, the hydraulic engineering scheduling simulation system comprises an acquisition component, a processing component, an analysis component and a scheduling simulation component, the analysis component comprises an ecological analysis unit, a collaborative scheduling unit and a dynamic scheduling management unit, and the scheduling simulation component performs linkage simulation, simulation scene setting, multi-dimensional verification and an exception handling mechanism. Multi-dimensional ecological parameters are integrated through the ecological analysis unit, ecological health is comprehensively and quantitatively evaluated to fill up the limitation of a single index, and multi-target parameters such as flood control and power generation are integrated through the collaborative scheduling unit and converted into unified priority to solve the problem of fuzzy scheduling targets. And the dynamic scheduling management unit integrates multiple detail parameters to generate an accurate and adaptive instruction, so that the execution effect is ensured, and the hydraulic engineering scheduling simulation system has excellent practicability.

The invention relates to the technical field of industrial automation control and dynamic simulation, and discloses a centralized control console and 3D model linkage virtual-real simulation system, which comprises a control signal sampling interface, a load response modulation unit, a dynamic model evolution unit and a virtual-real closed-loop feedback unit, the load response modulation unit performs energy consumption weight accumulation on all the virtual controlled objects in transient action to generate a global time scaling factor so as to correct an inertia time constant of the system in real time; the dynamic model evolution unit introduces a hard limiting boundary by using an amplitude limiting link and calculates a process variable; the virtual-real closed-loop feedback unit extracts a control deviation signal and drives a physical instrument to generate a nonlinear damping action, and by establishing a global load modulation model based on energy constraint, a discrete control system spontaneously emerges a nonlinear hysteresis characteristic conforming to physical energy conservation under the low calculation power condition without complex fluid network solution.

The invention relates to the technical field of new energy power distribution planning, in particular to a new energy power distribution planning intelligent simulation system oriented to a novel power system. Comprising a multi-source data dynamic modeling unit; the multi-objective optimization decision-making unit is used for realizing collaborative optimization of economy and reliability of the power distribution network and generating a planning scheme of equipment configuration, energy storage layout and network reconstruction by improving a heuristic algorithm; and the uncertainty analysis unit is used for quantifying the influence of the wind and light output fluctuation on the planning scheme and outputting a risk assessment index through a scene generation technology and a probability sampling method. Through multi-modal data fusion, time sequence model construction and a self-adaptive updating mechanism of the multi-source data dynamic modeling unit, the dynamic adaptation capability of the model to new energy power fluctuation and load characteristic change can be improved, and meanwhile, the space-time correlation characteristics between the source and the load are mined, so that the power grid model can be synchronously evolved along with the time sequence data change; and the deviation between the model and the actual operation condition is reduced.

The invention discloses a machine room energy efficiency optimization simulation system and method based on digital twinning, and relates to the technical field of machine room energy efficiency optimization. The system comprises a model construction and load analysis module, an equipment combination design module, an energy efficiency simulation calculation module and an optimal scheme adaptation and output module. According to the method, related parameters of a machine room are collected to construct a digital twinborn simulation model, different levels of load intervals are divided, a differentiated combination scheme composed of a high-voltage fixed-frequency large cold source unit and a low-voltage variable-frequency small cold source unit is designed for each interval, an energy efficiency optimal scheme is matched through simulation, a correlation database is established, and a result is output. Dynamic adaptation of the cold source equipment and the load interval is achieved, low-load energy efficiency attenuation is avoided, the full-working-condition energy efficiency of a machine room is remarkably improved, and reliable support is provided for optimal configuration of a cold source system.

The invention discloses a six-degree-of-freedom multi-spacecraft control experiment platform and method based on semi-physics-virtuality, belongs to the technical field of spacecraft system and control system simulation, and constructs a multi-spacecraft system composed of semi-physics spacecrafts and pure virtual spacecrafts. The attitude of the semi-physical spacecraft is simulated by a simulator mounted on a three-dimensional attitude air floating table, is acquired by a sensor and is converted into a rotation matrix form, and a translation part of the semi-physical spacecraft is virtually calculated through a simulation integrator; the pose of the virtual spacecraft is virtually simulated by an SE (3) integrator with high-guarantee geometric characteristics; the system takes the ROS as a communication framework, and realizes state and instruction release by adopting a custom message; and ensuring that the time system of each spacecraft is consistent with the real time through a time synchronization mechanism. The platform supports cooperative operation of a semi-physical spacecraft and a pure virtual spacecraft, and has the characteristics of flexible structure, high simulation precision and good expandability.

The invention belongs to the technical field related to energy storage safety, and particularly relates to a simulation method, a simulation device and a simulation system for container shipping vibration. A sea wave spectrum model and a cargo ship model are obtained, and a time domain signal is obtained according to the sea wave spectrum model; defining the time domain signal as fluid excitation, and obtaining a first response signal of a preset acquisition point of the cargo ship model according to the fluid excitation; acquiring a frequency domain sequence according to the first response signal, and calculating and acquiring power spectral density according to the frequency domain sequence; obtaining a container model, and calculating and obtaining a second response signal of the container model according to the power spectral density; whether the container of the current cargo ship meets the safety requirement or not is judged according to the second response signal. Safety simulation is carried out on the energy storage container body during marine transportation, so that mechanical damage caused by design problems during marine transportation of the designed energy storage container is avoided.

The invention relates to a reconfigurable equipment simulation system based on software radio, and the system achieves the high-integration, user-friendly and efficient-management reconfigurable equipment simulation system through the modularization and seamless integration of a radio waveform design function, an equipment simulation user operation interface design, a business logic function design and a project management function. Therefore, even if a user does not have a deep programming capability, the user can quickly construct, test, manage and deploy the equipment simulator with complete functions. The system is rich in waveform component and UI component library, customizable in function and good in flexibility, software radio waveform design and equipment simulation are innovatively and seamlessly integrated, automatic non-inductive or manual upgrading can be achieved, the universality is good, various equipment simulators can be designed, the designed equipment simulators have open function expansion, and the system is suitable for popularization and application. And a complete project management process is provided.

The invention provides a system platform and method for checking adjustment characteristics of a control system based on semi-physical simulation, and belongs to the technical field of power system control equipment detection. The system comprises an all-digital real-time simulation system (ADPSS), a water turbine governor to be tested, a physical interface communication module, a wave recording device and a signal interaction module. A full-electromagnetic example model constructed based on PSASP is built in the ADPSS, a closed-loop detection environment is constructed through the physical interface communication module and a water turbine governor to be detected, bidirectional signal transmission is achieved through the signal interaction module, and key parameters are recorded through the wave recording device. The method comprises the steps of simulation environment establishment, signal interactive transmission, multi-dimensional detection and check and result judgment and output. According to the method, multi-dimensional checking of the speed regulator acquisition and display function, the transfer function consistency, the grid-connected performance and the like and power grid stability influence verification can be completed without field installation, the coverage scene is comprehensive, the checking precision is high, and the method is suitable for performance detection of different types of speed regulators and has remarkable practical value.

The invention relates to an automatic driving training method and system based on a differentiable world model simulation system, computer equipment and a medium. The method comprises the following steps: constructing the differentiable world model simulation system; the differentiable world model simulation system comprises a differentiable sensing module, a dynamic model and a strategy network; freezing the strategy network, and pre-training the differentiable world model simulation system by using the first training data; unfreezing the strategy network, and performing end-to-end joint optimization on the differentiable world model simulation system by utilizing the second training data and adopting a course learning strategy; and carrying out safety strengthening training on the differentiable world model simulation system by utilizing the third training data. According to the method, the full link is automatically driven, namely, perception, prediction and planning end-to-end differential is achieved, the training efficiency is improved, and the generalization of a long-tail scene is improved.

The present application relates to the technical field of intelligent war game, in particular to an intelligent war game simulation system based on digital twin fusion large model, which comprises a digital twin modeling unit, a large model decision unit, a deduction execution unit and a dynamic interaction unit. The digital twin modeling unit adopts a dynamic precision adaptive modeling mechanism, which can realize dynamic switching of model precision on demand, balance the demand for detailed simulation and the consumption of computing resources, and realize sub-second dynamic synchronization of virtual models and war game scenes through a timing calibration algorithm. Through the multi-modal feature analysis module, spatial adversarial, timing decision and rule trigger features are fused, and the entity performance boundary and scene rule constraint are embedded in the war game rule verification module, which can generate compliant adversarial decision parameters in line with the logic of war game, solving the problem of insufficient model precision adaptation and decision constraint.

Systems and methods for fully automated anatomical analysis of an anatomical structure are provided to facilitate pre-operative planning. The computerized method may include obtaining a plurality of images, e.g., MSCT images, of patient-specific cardiovascular anatomy, and analyzing the MSCT images with a trained artificial intelligence module to identify one or more anatomical landmarks and to construct a virtual three-dimensional model of the anatomical structure. For example, the trained artificial intelligence module may execute segmentation, point detection, curve detection, or plane detection deep learning modules, independently or in combination, to identify the anatomical landmarks. The method further may include deriving anatomical measurements of the one or more identified anatomical landmarks, and displaying the virtual three-dimensional model alongside the anatomical measurements of the one or more identified anatomical landmarks.

The invention provides an intelligent landslide rainfall simulation system and method based on AI historical rainfall data driving, and belongs to the technical field of geological disaster monitoring and early warning. Dynamic coupling analysis and high-precision simulation of the rainfall process and slope stability are realized through automatic fusion of multi-source monitoring data and spatial-temporal feature extraction in combination with deep learning and physical mechanism modeling. The system can sense various types of data such as rainfall, soil moisture content and slope deformation in real time, intelligently identify landslide induced risks, output graded early warning information and support digital twinborn and adaptive risk optimization decisions. The landslide disaster risk assessment and early warning accuracy and response timeliness are remarkably improved, and the method has good intelligence, expansibility and practical application value and is widely applied to the fields of geological disaster prevention and control and engineering safety monitoring.

Techniques are discussed herein for generating and evaluating driving simulations based on synthetic scenarios. Simulated objects may be controlled based on parameters determining the attributes and behaviors of the objects, and scenarios may be synthetically modified by changing the parameters for a simulated object. For a driving scenario with a synthetic simulated object, a simulation system may analyze driving log data to determine a probability or prevalence associated with the driving scenario. In various examples, the simulation system may determine marginal density estimates for individual attributes of the simulated object, as well as a cumulative distribution function modeling the dependence between the attributes. The joint probability distribution determined for the synthetic simulated object can be used for evaluating the efficacy of the simulation and the performance of the simulated vehicle controllers.

The invention relates to a tilt rotorcraft semi-physical simulation system and method, and relates to the technical field of wind tunnel flight test semi-physical simulation. Based on the initialized system with the test parameters set, six-component balance load, wind speed and attitude data are collected in real time, and the collected key physical data are filtered and then sent to the flight simulation subsystem; the flight simulation subsystem carries out calculation based on a flight dynamics model, a rotor wing power model, a control instruction preprocessing model and the received data and outputs an actuation instruction; the actuator receives an actuation instruction and drives the aircraft model, and the airborne sensor feeds back new attitude data to form a control closed loop; the flight simulation subsystem sends state data to the 3D visual simulation module in real time to realize synchronization of control and visual; in this way, the stable state under the combination of different tilting angles and flight speeds is recorded, and a tilting transition corridor is obtained through fitting. Therefore, simulation precision, test safety and iteration efficiency are taken into consideration, and fused semi-physical simulation is formed.

The invention discloses a cooperative control simulation system for an underwater robot and an umbilical cable system, belongs to the technical field of ocean engineering simulation and automatic control, and is used for analyzing system dynamic characteristics in the research and development stage of deep sea operation equipment. Comprising an environment initialization and marine environment construction module, a mother ship model construction module, an underwater robot and umbilical cable coupling module, an instruction generation module, a man-machine interaction control module and a data acquisition and storage module. According to the method, an external interference source with physical authenticity is provided for a control algorithm by combining an energy density function and simulating a composite environment modeling method of a sea level height field and an LOD dynamic grid, and a distributed model prediction control algorithm for uniformly optimizing underwater robot trajectory tracking and umbilical cable tension safety maintenance is constructed; data such as the motion state of the underwater robot and the tension of the umbilical cable can be output in real time, algorithm performance testing is completed in a virtual environment, and dependence on high-cost sea testing is not needed.

The invention relates to a rock core seepage heat exchange dynamic coupling simulation system based on outlet temperature feedback. The system comprises a multi-medium precise injection system, a gradient temperature control rock core clamping system, an outlet multi-dimensional information sensing system, a dynamic coupling central control system and a pressure compensation and circulation backflow system. The central control system receives feedback signals of the outlet end and adjusts injection power and an axial gradient temperature control area in real time, and deep dynamic coupling of a seepage field, a temperature field and a stress field is achieved. The problems that a traditional experiment is constant in injection temperature and lacks outlet feedback are solved, real stratum temperature scale distribution can be accurately reconstructed, the physical fidelity and data reliability of a heat exchange coupling experiment are remarkably improved, and an advanced experiment supporting platform is provided for basic mechanism research in the field of energy development.

The invention relates to the technical field of oil and gas field development, in particular to an ultra-deep gas well production string multi-mode leakage simulation experiment device and method. According to the technical scheme, the outer side of a shaft temperature and pressure coupling simulation system is connected with a reservoir gas supply simulation system, the middle of the shaft temperature and pressure coupling simulation system is provided with a multi-mode leakage simulation assembly, the lower end of a production oil pipe is connected with a reservoir-shaft coupling connector, and the upper portion of one side of a layered sand filling seepage tank of the reservoir gas supply simulation system is connected with a confining pressure loading unit through a pipeline; the lower portion of the layered sand filling seepage tank is connected with a reservoir fluid supply unit, and the outlet end of the layered sand filling seepage tank is connected with a reservoir-shaft coupling connector through a pipeline. The experimental device has the beneficial effects that the experimental device for coupling the reservoir and the shaft is constructed, and the multi-mode leakage simulation assembly is adopted to realize body perforation leakage simulation and screw thread sealing failure simulation, so that the simulation of the ultra-deep gas well under complex working conditions is realized, and a scientific basis and a technical support are provided for leakage prevention and control of a production string of the ultra-deep gas well.

The invention discloses a tractor dynamic load reliability coupling test system and method, and belongs to the technical field of non-road vehicle testing. The system comprises a multi-dimensional data management platform, a tractor dynamic load reliability coupling test bench, a performance analysis platform and a data server. The multi-dimensional data management platform collects field working condition data and test data, the test bench integrates a plurality of loading systems and simulation systems such as direct-drive type driving wheels, and a plurality of functional parts of the tractor can be dynamically coupled, loaded and tested at the same time in a simulated field environment; and the performance analysis platform is connected with the data server, and evaluates the comprehensive performance and reliability of the whole tractor and the functional parts thereof through a quantitative formula. According to the invention, indoor reproduction of a field operation scene is realized, test efficiency and reliability evaluation comprehensiveness are improved, and the method is suitable for whole tractor performance test.

The invention relates to the technical field of medical image processing and surgical navigation, in particular to a liver segmentation, modeling and surgical simulation system based on a cascade neural network and a multi-scale reconstruction technology. The multi-scale dynamic registration module is used for carrying out coarse segmentation and fine segmentation on liver and focus areas of the medical image and is used for non-rigid registration and respiratory motion compensation of the multi-modal medical image; the physical enhancement modeling engine is used for constructing a liver vessel tree three-dimensional model containing hemodynamic characteristics; the operation navigation and risk assessment module is used for performing real-time navigation and operation path planning in the operation; and the self-adaptive computing framework provides underlying computing resource support for the system. And high-precision segmentation: through a cascade recursive network and a boundary sensitive loss function, the liver tumor segmentation Dice coefficient reaches 94-96%, which is increased by 6-12% compared with the traditional method.