75 results about "Eulerian lagrangian" patented technology

The invention discloses a four-rotor unmanned aerial vehicle model prediction control method based on a deep Q-network (DQN). The method comprises the following steps: firstly, establishing an inertial coordinate system and a body coordinate system, and establishing a kinematic equation and a kinetic equation of the four-rotor unmanned aerial vehicle based on a Newton second law and an Euler-Lagrange equation; according to the method, an unmanned aerial vehicle robust controller based on model predictive control (MPC) is designed, optimal control input is generated through dynamic optimization, and the trajectory tracking performance of the unmanned aerial vehicle is improved. For various disturbances existing in the whole tracking process, a DQN reinforcement learning algorithm and an MPC method are combined to design a flight control system, control rate errors caused by the disturbances are compensated, the stability of attitude control is enhanced, and the tracking precision and the anti-interference capability are improved. And finally, verifying the robust performance of the flight control system through a simulation experiment.

The invention relates to the technical field of underground engineering and geotechnical mechanics, and provides an ABAQUS secondary development-based underground engineering blasting simulation method, which comprises the following steps of: 1, establishing a geometric model and dividing a calculation region into an Euler domain and a Lagrange domain; step 2, calling and realizing a JH-2 constitutive model through a UMAT user subprogram interface of the ABAQUS; step 3, modeling in an Euler domain by adopting a JWL state equation; step 4, applying a coupling Euler-Lagrange method; 5, setting boundary conditions and blasting loading parameters of the geometric model; and step 6, performing transient dynamics calculation, and outputting a result for analyzing a blasting effect. According to the scheme, a high-precision numerical test platform can be provided for underground engineering blasting design and safety control, engineering risks are reduced, blasting parameter configuration is optimized, and remarkable engineering application value and popularization significance are achieved.

The invention discloses a soft air refueling hose-taper sleeve dynamic response process analysis method, and relates to the technical field of airplane soft air refueling process dynamic response analysis. The aerodynamic force of the refueling hose is simulated by loading the aerodynamic force on the refueling hose, the aerodynamic force of the taper sleeve is simulated by loading the aerodynamic force on the taper sleeve, and hose-taper sleeve dragging balance process modeling is carried out on a beam unit of the hose through an absolute node coordinate method. The method comprises the following steps: modeling a hose-taper sleeve system extension release stabilization process through an absolute node coordinate method based on any Euler Lagrangian description, then loading an external force and determining a boundary condition; constructing and solving a hose-taper sleeve drag balance process multi-body dynamics equation set and a hose-taper sleeve release stability process multi-body dynamics equation set, so that the drag balance process and the extension release stability process of the hose-taper sleeve system can be accurately simulated; and the analysis accuracy of dynamic responses such as hose shape change and taper sleeve posture change is improved.

The invention discloses an external mixing type air nozzle atomization process simulation method, which comprises a multi-scale atomization mathematical model and numerical simulation based on the multi-scale atomization mathematical model, the multi-scale atomization mathematical model divides a flow field component into a continuous phase and a dispersed phase based on an Euler-Lagrange coupling method, the Lagrange method is used for describing the movement of small-scale coating particles, and the numerical simulation is carried out based on the continuous phase and the dispersed phase. Establishing a big and small droplet identification conversion mechanism, and selecting Reynolds average simulation to establish a turbulence model; based on numerical simulation of a model, a geometric model is firstly constructed to generate a computational domain, a coordinate system is established, then a key region is divided and encrypted by using a hybrid grid, and simulation is performed by controlling the number of grids in combination with a dynamic adaptive technology. Direct and indirect verification experiments prove that the model is correct; the problems that an existing model is incomplete in description, poor in fidelity and low in calculation efficiency are solved, the time cost is saved, the simulation result is closer to reality, accurate data can be provided for analysis of the atomization phenomenon, and the spraying quality and the production efficiency are improved.

The invention discloses a cooperative online and offline control method for an unmanned aerial vehicle power transmission line broken strand repairing robot, and aims to realize efficient and safe maintenance of a power transmission line. Based on Newton-Euler and Euler-Lagrange equations, establishing an eight-degree-of-freedom nonlinear dynamic model of the unmanned aerial vehicle-broken strand repair robot; and designing and optimizing an extended state observer and a nonlinear error feedback control law to suppress swinging. An airborne visual servo system is adopted to capture the posture of the robot so as to correct the trajectory of the unmanned aerial vehicle, and a double-closed-loop control strategy based on a spherical swing mechanism is applied to realize stable tracking of an arc trajectory. Nonlinear load trajectory tracking control based on a six-dimensional force sensor is introduced, suspension point tension and the position of the unmanned aerial vehicle are fused to estimate the pose of the robot, self-adaption to different load weights is achieved through a load speed observer, and real-time data exchange between the unmanned aerial vehicle and the robot is supported through a low-delay and high-reliability communication protocol.

The invention relates to a method for rapidly predicting particle rotation of a cyclone based on data driving, which comprises the following steps of: carrying out CFD numerical simulation through an Euler-Lagrange coupling model, combining PIV (particle image velocimetry) measurement and high-speed camera experiment data, and dynamically fusing multi-source data by adopting Kalman filtering to construct a mixed data set; in the feature engineering stage, thousand-dimensional flow field data are compressed to 50-dimensional through PCA dimension reduction and an auto-encoder, and key physical quantities such as centrifugal acceleration, shear stress and vorticity are weighted and fused. A multi-model collaborative prediction system (BP / XGBoost / CATBoost / RF / AdaBoost / SVM) is innovatively constructed, and algorithm advantage complementation is realized through dynamic weight fusion (error reciprocal distribution + abnormal weight drop). Classified hyper-parameter optimization (Bayesian optimization tree model depth / learning rate, grid search SVM kernel parameters) is adopted, TensorRT quantization (FP16) and ONNX conversion are combined, and the inference speed of embedded deployment reaches 48 ms. And the prediction result drives the PID controller to accurately adjust the inlet flow in real time. And through data-driven modeling and interpretability analysis, an efficient solution is provided for cyclone optimization control.

This invention discloses a spatial domain impedance learning control method for a five-bar parallel robot, comprising the following steps: Step 1, establishing an Eulerian-Lagrange model of the five-bar parallel robot; Step 2, establishing a human-machine system interaction force model based on the trajectory tracking error of the parallel robot; Step 3, estimating impedance dynamics based on the Eulerian-Lagrange model; Step 4, designing an iterative learning strategy for human-machine interaction force based on the human-machine system interaction force model and impedance dynamics; Step 5, conducting control tests on the five-bar parallel robot using the iterative learning strategy for human-machine interaction force. The learning control method proposed in this invention ensures the convergence of tracking errors, considers the uncertainties in robot modeling, and further guarantees the safety of human-machine interaction.

The application discloses an analysis method for key local vibration of fluid-solid coupling bridges based on a substructure method, and relates to the technical field of bridge vibration analysis, and comprises the following steps: dividing a response key area in a bridge structure into substructures, performing static condensation, and obtaining a condensed substructure model; establishing a whole bridge-wave coupling model, and adopting a dynamic explicit solving strategy based on a coupling Euler-Lagrange method; independently solving the substructures by using a dynamic implicit method; coupling the substructures to the whole model by an interface coordination condition, and jointly calculating the whole explicit model and the local implicit model. The analysis method adopts an explicit method to process a strong nonlinear fluid-solid coupling process at a whole level, and establishes a fine substructure model through Guyan static condensation at a local area, so that the analysis precision is effectively improved.

The application discloses a tethered multi-robot formation deployment control method based on tension input quantization, which is composed of the following steps: step S1: a dynamics model of a tethered multi-robot formation system is established according to kinetic energy, potential energy, elastic potential energy and geometric constraint relationship of the tethered multi-robot formation system combined with an Euler-Lagrange method, step S2: an estimated value of external disturbance is obtained by estimating the external disturbance of the dynamics model by using an extended state observer, step S3: a preset time sliding mode control input value is obtained by using a sliding mode control method combined with a preset convergence time, step S4: the preset time sliding mode control input value is converted into a plurality of segmented continuous quantization input values by a quantizer, and step S5: a control method of the multi-robot formation is designed by inputting the plurality of quantization input values and the estimated value of the external disturbance into the dynamics model; the application can reduce the communication burden of the system, reduce the frequency of the actuator update, and ensure the stable deployment of the space multi-tethered robot.

A transmission conductor glaze ice coating growth modeling and simulation method comprises the steps that an air flow field control equation is established, and the local collision coefficient of water drops and the surface of a conductor is solved based on the Euler-Lagrangian method; the method comprises the following steps: dispersing the surface of an iced conductor into a plurality of infinitesimal control bodies, establishing a mass conservation equation of each infinitesimal, and carrying out partition modeling on a surface thin water film flow process; constructing an infinitesimal energy conservation equation according to a thermodynamic equilibrium principle, and calculating a water drop freezing coefficient by balancing multiple energy input and output items; combining the collision coefficient and the freezing coefficient to establish an icing growth thickness calculation model; and setting physical parameters and boundary conditions in a finite element simulation environment, and simulating an icing growth process to obtain a glaze icing three-dimensional shape. According to the method, icing key parameters can be accurately calculated, the relative error between a simulation result and actual icing is lower than 5%, the defect of a wet growth icing theory is overcome, data support is provided for torsion, galloping and other problems caused by wire icing, and power transmission line icing prediction, analysis and prevention and control can be assisted.

The invention discloses a dendritic crystal growth and motion simulation method and system based on an Euler-Lagrangian method.The method comprises the steps that firstly, a phase field model is constructed based on convection flux in a solute field; solving liquid convection on an Euler background grid, and solving solid motion through a Lagrange grid; and updating the moved solid boundary through the conservative phase field model. According to the method, on the basis of simulation of the growth condition of the dendritic crystal, the Lagrange grid is introduced into the discrete interface to simulate the motion behavior of the dendritic crystal, the alloy growth morphology and convection motion are simulated at the same time, the problem that the speed between the grid and the fluid is not matched is solved, and the problem of topological change of a complex interface is solved.

The application relates to the technical field of underground engineering and geotechnical mechanics, and provides an underground engineering blasting simulation method based on secondary development of ABAQUS, which comprises the following steps: step 1, a geometric model is established, and a calculation region is divided into an Euler domain and a Lagrange domain; step 2, a JH-2 constitutive model is called and realized through a UMAT user subroutine interface of ABAQUS; step 3, a JWL state equation is used for modeling in the Euler domain; step 4, a coupled Euler-Lagrange method is applied; step 5, boundary conditions and blasting loading parameters of the geometric model are set; and step 6, transient dynamics calculation is carried out, and results are output for analyzing blasting effects. The scheme not only can provide a high-precision numerical test platform for underground engineering blasting design and safety control, reduces engineering risks, optimizes blasting parameter configuration, but also has remarkable engineering application value and popularization significance.

The invention relates to the technical field of industrial dust removal equipment design and fluid simulation, and discloses a macroscopic numerical simulation and verification method for dust deposition uniformity of a metal filter bag deduster, which comprises the following steps: constructing a deduster full-size model loaded with a porous jumping medium boundary; establishing an Euler-Lagrange gas-solid coupling model to calculate a flow field and a particle trajectory; designing a diversion structure orthogonal experiment based on the flow field characteristics, and obtaining operation resistance and deposition mass data under different parameter combinations; establishing an evaluation system comprising a flow distribution coefficient and a deposition uniformity index, and screening an optimal structure; a physical experiment platform is constructed for powder coating and segmented scraping weighing, and the reliability of the method is verified by comparing relative errors of experiments and simulation data. According to the method, through macroscopic equivalent modeling and quantitative evaluation, the deposition behavior in the metal filter bag dust collector is accurately predicted, the problem of uneven load of the filter bag is effectively solved, and a reliable basis is provided for structural optimization.

The present invention relates to the technical field of tunnel safety assessment, and discloses an assessment method, system and device for the safety of tunnel linings, including: obtaining the design parameters of the tunnel structure, and constructing an Euler-Lagrange model according to the design parameters; respectively changing each model parameter in the Euler-Lagrange model, and calculating the critical value of the circumferential angle of contact loss when the tunnel structure is damaged under different model parameters; constructing a judgment model according to different model parameters and the corresponding critical values; the judgment model is used to input each model parameter and output the safety assessment result of the tunnel structure; obtaining the tunnel burial depth, contact loss position, longitudinal range of each contact loss and circumferential angle of each contact loss of the tunnel structure to be measured, and inputting them into the judgment model to output the safety assessment result of the tunnel structure to be measured. The advantage of this application is to provide an effective tunnel operation stage safety assessment system to monitor the safety state of the tunnel in real time.

The application belongs to the field of robot control, and particularly relates to a mobile robot dynamic event triggering control method based on reinforcement learning. In view of the unknown wheel slip effect of the robot and the communication resource constraint problem, a kinematics model and an Euler-Lagrange dynamics model of a four-wheel Mecanum wheel mobile robot are established, the motion deviation caused by four-wheel slip is characterized as non-matching disturbance, the trajectory tracking problem is converted into an extended dimension system adjustment problem constrained by the worst case disturbance by combining the tracking error and the expected trajectory and introducing the steady state control, a dynamic event triggering mechanism is introduced to reduce the calculation burden and transmission load, a Critic reinforcement learning algorithm is designed to solve the Hamilton-Jacobi-Isaacs equation to obtain an approximate optimal controller under the dynamic event triggering condition, and the consistent ultimate bounded stability of the closed loop system is analyzed based on the Lyapunov theory, so that the high-precision trajectory tracking performance of the robot is ensured on the premise of saving communication and calculation resources.

The invention discloses a double-collision double-tuned damper for controlling transverse vibration of a floating fan tower, which is designed by the following steps of: constructing a single-column floating fan model; describing the movement of the single-column floating fan by adopting an Euler-Lagrange method and multi-body dynamics; and finally, substituting the kinetic energy and the potential energy into an Euler-Lagrange equation and carrying out linearization to obtain a mass matrix, a stiffness matrix and a damping matrix of the floating fan. DPDTMD design: coupling the kinetic energy and potential energy of the DPDTMD with the kinetic energy and potential energy of the floating fan, and finally obtaining a mass matrix, a stiffness matrix and a damping matrix of a motion equation of the single-column floating fan under the control of the DPDTMD through an Euler-Lagrange equation; dPDTMD parameter optimization includes the mass, rigidity and damping of the two dampers, the installation position of the limiting stopper and the collision rigidity and recovery coefficient of the collision material. On the basis of ensuring the control effect and robustness of the damper, the maximum stroke of the vibration absorber is limited.

The invention discloses an analysis method for key local vibration of a fluid-structure interaction bridge based on a substructure method, and relates to the technical field of bridge vibration analysis, and the method comprises the following steps: dividing a response key region in a bridge structure into substructures, and carrying out static polycondensation to obtain a polycondensed substructure model; an integral bridge-wave coupling model is established, and a dynamic explicit solving strategy based on a coupling Euler-Lagrange method is adopted; independently solving the substructures by adopting a dynamic implicit method; and coupling the substructures into the overall model through an interface coordination condition, and carrying out joint calculation of the overall explicit model and the local implicit model. According to the analysis method, an explicit method is adopted to process the strong nonlinear fluid-solid coupling process on the overall level, a fine substructure model is established in a local area through Guyan static polycondensation, and the analysis precision is effectively improved.

The invention belongs to the technical field of robot control, and particularly relates to an anti-disturbance multi-finger cooperative grabbing control method with global preset performance, which comprises the following steps: establishing a kinetic model of a dexterous hand system according to an Euler-Lagrange equation; describing a communication topological structure of the dexterous hand system through a virtual coupling mechanism, and constructing a collaborative grabbing error of the dexterous hand system; a preset time function and a global preset performance function are introduced to convert the collaborative grabbing error, and the overall potential energy of the dexterous hand system is calculated; with the purpose of minimizing the overall potential energy of the dexterous hand system, joint control input torque is designed in combination with a distributed control architecture; designing a self-adaptive updating law for unknown disturbance according to an internal model principle, and obtaining a distributed global preset performance control law in combination with a joint control input torque; according to the method, the robustness of the system under disturbance of joints and external force is remarkably improved.

The present invention discloses a method for predicting the dynamic response of a plate frame structure under underwater explosion load based on a convolutional neural network, which belongs to the technology of ship damage under underwater explosion load. The method first uses CEL to perform numerical simulation on the dynamic response of the plate frame structure under underwater explosion load to obtain data samples; generates different explosive equivalent-damage picture sets according to the damage caused to the plate frame by different equivalent explosives; performs dimensionality reduction processing on the aforementioned data samples according to the symmetrical structure of the plate frame; binds the reduced-dimensional data to the picture set; executes a convolutional neural network training program, uses the reduced-dimensional data and the picture set to train and obtain training results; executes a neural network training program, trains the input explosive equivalent-damage picture and the displacement data of each node of the plate frame, so that the explosive equivalent-plate frame damage-displacement of each node of the plate frame form a fitting relationship to achieve the purpose of prediction. The present invention uses a coupled Euler-Lagrangian method (CEL) to perform numerical simulation to obtain a database, trains the convolutional neural network based on the numerical calculation results, and realizes the rapid prediction of the dynamic response of the plate frame structure under underwater explosion load.

The present application relates to the technical field of self-balancing vehicle control, and discloses a self-balancing vehicle control method, system, storage medium and electronic device, including: collecting actual operation state data of the self-balancing vehicle; estimating the Lagrangian of the system by using a neural network learning system; obtaining an estimated vector field of the system and calculating an estimated system state by using the Euler-Lagrange equation; updating the neural network parameters by using the backpropagation algorithm to obtain an accurate estimate of the Lagrangian; designing a damped PD controller according to the accurate Lagrangian to achieve accurate control of the self-balancing vehicle. This method reduces the dependence of controller design on an accurate model of the system, improves the robustness of the controller to an uncertain model and the adaptability to a dynamic model; the learning framework of the Lagrangian neural network is based on physical information, improves the interpretability of controller design, and reduces the requirement for the amount of data in the learning process.

The present invention relates to the technical field of streamlined demister design, and in particular to a streamlined demister design method based on a probability model, comprising the following steps: step S1: analyzing and calculating the demisting rate λ and the total pressure loss Δp of a single bend in a single channel; step S2: determining the gas flow rate, bend spacing, bend angle, demisting rate λ, and total pressure loss Δp with the highest demisting efficiency i; step S3: equating the demisting rate λ to the absorption probability P of droplets; step S4: equating the process of n bends absorbing droplets to a series of independent random events; and step S5: calculating the demisting failure probability 1-P(A) for each bend. i ); Step S6: After the droplet passes through the n folding plates, the absorption probability of the droplet is 1-(1-P) n ; Step S7: Let 1-(1-P) n ≥99%, and the number of bends n required for the demister is calculated; this solves the problems of large computational complexity and low efficiency in the existing design of streamlined demisters using the Euler-Lagrange coupling numerical method.

The invention discloses a railway cutting sand retaining wall design optimization method based on analogue simulation. The method comprises the steps that a three-dimensional anemograph array and a rotary vortex detector are arranged outside a sand retaining wall; establishing a three-dimensional model of the sand retaining wall based on environmental data collected by the three-dimensional anemograph array and the rotary vortex detector; based on the established three-dimensional model of the sand retaining wall, adjusting the height of the sand retaining wall, putting the adjusted environmental data into a gas-solid two-phase flow model under an Euler-Lagrange framework, and determining an optimal height; after the optimal height is selected, the porosity is adjusted, the adjusted environment data are put into an Euler-Lagrange vortex flow model, and the optimal porosity is determined; and based on the optimal height and the optimal porosity data, an optimized sand blocking wall is established, and a preset weather guarantee measure system is established. The method has the beneficial effects that the unit sand interception effect is improved, the life cycle of the railway cutting can be prolonged at low cost, and the dynamic balance between the protection strength and the energy consumption is achieved.

The invention discloses an image segmentation method of a parametric type active contour model based on Finsler-Laplacian. According to the method, an anisotropic Finsler norm is introduced under a static external force field, and a new energy minimization problem is provided and comprises a data fidelity term and a regularization term based on the Finsler norm. A corresponding Euler-Lagrange equation is derived through a variational method and is converted into a time-evolved parabolic partial differential equation for numerical solution. A comparison principle is established under the framework of the viscous solution, and the existence of the understanding, the continuity about the space Lipschitz and the continuity about the time consistency are proved. The model has the advantages of being large in capture range, insensitive to initial contours, high in noise immunity, capable of effectively retaining image edge details and the like, and shows excellent performance in medical image and natural image segmentation.

The application relates to the technical field of automatic control, in particular to an anti-interference control method and system for an Euler-Lagrange system containing unknown interference, the method comprising the following steps: establishing an Euler-Lagrange dynamics model containing unknown interference and model uncertainty, unifying the unknown interference and the model uncertainty into a bounded and differentiable lumped disturbance term, constructing a preset time disturbance observer to perform specified time estimation on the lumped disturbance term; defining a system tracking error, designing a non-singular preset time synchronous sliding mode surface fused with a time-varying scaling function; and based on the output value of the preset time disturbance observer and the non-singular preset time synchronous sliding mode surface, designing a preset time synchronous controller with disturbance feedforward compensation. Under the premise of considering unknown interference and system uncertain dynamics, the system interference and uncertainty can be effectively reconstructed, the anti-interference capability of the system is improved, and vibration suppression and attitude stabilization are realized.

The invention discloses a projectile high-speed penetration icebreaking water entry simulation method and system. The method mainly comprises the steps that a projectile high-speed water entry calculation model is established based on an Euler-Lagrange coupling method; an ice layer failure fracture model is established according to the failure damage form of the ice layer under the high strain rate; according to the constitutive relation of the metal structure material, a Johnson-Cook constitutive equation and a damage model are adopted to reflect the strain performance of the metal material; the interaction between the projectile and the fluid and the interaction between the ice layer and the fluid are defined through universal contact, and the contact behavior between the projectile and the ice layer is defined through surface-surface contact; a penalty function method is adopted to process the strong coupling process in the high-speed collision of the projectile and the ice layer; based on a projectile high-speed water entry calculation model, an ice layer failure fracture model, the strain performance of a metal material, the interaction between the projectile and fluid, the interaction between the ice layer and the fluid, the contact behavior between the projectile and the ice layer and the strong coupling process, numerical simulation is conducted on projectile penetration icebreaking water entry, and cavitation evolution and trajectory characteristic information is obtained.

This invention belongs to the field of robotic arm control and provides a robust control method and system for a lifting robotic arm. It includes determining five nonlinear motion equations of the robotic arm dynamics using the Euler-Lagrange equations and representing them in matrix form. The robotic arm dynamics matrix form is divided into driven and non-driven forms, and after reduction processing, a reduced-mode dynamic model of the robotic arm is obtained. A robust controller is constructed by building a second-order sliding mode controller and a fast terminal sliding mode controller. The robotic arm dynamics matrix form is transformed into a state-space form to obtain a state observer. The state observer is subtracted from the state-space form to obtain the estimation error dynamic equation. The dynamic state of the robotic arm is inferred using the state observer. The control mode of the robust controller is determined based on the estimation error dynamic equation corresponding to the dynamic state, and the corresponding control signal is generated based on the robust controller. This invention significantly improves the safety and efficiency of robotic arms in practical applications.

The present invention proposes a fine-grained human action generation method based on physical laws and skeleton guidance. First, relevant action videos are obtained online, and two-dimensional postures are extracted from the videos as prior information of the human physical structure. The transformation from 2D postures to 3D postures is achieved through a context learning method to enhance spatial perception, and a data-driven three-dimensional skeleton sequence #imgabs0# is obtained. Further, a physical module PhysNet is designed to re-estimate human actions using the Euler-Lagrange formula, calculate joint accelerations bidirectionally in time series, and thus generate physically predicted three-dimensional postures #imgabs1#. Then, the physically estimated three-dimensional postures #imgabs2# are fused with the data-driven three-dimensional skeleton sequence #imgabs3# and converted into a 2D heatmap format to participate in 3D-UNets for video generation. The present invention is tested on three subsets of fine-grained action data, and FinePhys far exceeds other video generation methods. A large number of qualitative analyses further prove that FinePhys can generate more natural and reasonable fine-grained human actions.

The invention provides a fine-grained human body action generation method based on a physical law and skeleton guidance, which comprises the following steps: firstly, acquiring a related action video in an online mode, and extracting a two-dimensional posture from the video as prior information of a human body physical structure; realizing conversion from a 2D attitude to a 3D attitude through a context learning method so as to enhance spatial perception, and obtaining a data-driven three-dimensional skeleton sequence # imgabs0 #; further designing a physical module PhysNet, re-estimating human body actions by using an Euler-Lagrange formula, and bidirectionally calculating joint acceleration in a time sequence so as to generate a physically predicted three-dimensional posture # imgabs1 #; and then, fusing the physically estimated three-dimensional attitude # imgabs2 # with a data-driven three-dimensional skeleton sequence # imgabs3 #, and converting the fused three-dimensional attitude # imgabs2 # and the fused three-dimensional skeleton sequence # imgabs3 # into a 2D heat map format to participate in 3D-UNts to realize video generation. According to the method, testing is carried out on three types of fine-grained action data subsets, FinePhys far exceeds other video generation methods, and a large amount of qualitative analysis further proves that FinePhys can generate more natural and reasonable fine-grained human body actions.

A method for designing lithology-specific drill bits. The method creates an experimentally verified multiphysics model to predict drilling into site-specific rock formations. A physics-based, Eulerian-Lagrangian computational modeling framework to predict particle flow and tribological phenomena. The method uses this multiphysics model to generate virtual drilling data and then generates a machine learning enabled surrogate model of the physics-based model using the data from virtual drilling to provide design charts for drill bits.

The application belongs to the technical field of motor system control, and discloses a motor feasible task design method based on motor performance parameters and controller structure, which comprises the following steps: first, determining two types of motor performance parameters of the maximum torque and the peak power of the selected motor; second, based on Euler-Lagrange equation, establishing motor dynamics differential equation containing unknown rotational inertia, unknown friction resistance, and describing the characteristics of motor generalized speed; third, designing an adaptive controller to realize speed tracking control and online estimation of unknown rotational inertia, unknown friction resistance and unknown external disturbance; fourth, based on motor performance parameters and adaptive controller structure, establishing task feasibility constraint inequality, and determining motor feasible task in combination with the task load condition. The application can realize the analysis and determination of motor feasible task based on the control strategy and the maximum speed and the maximum torque of the motor without experimental test.