18 results about "Longitudinal model" patented technology

The invention relates to the technical field of automatic driving trajectory planning control, in particular to an optimal inter-vehicle time interval control method for cooperative cruise of a truck under a communication delay condition. According to the method, a layered control framework of truck cooperative cruise control is designed, and a vehicle safety inter-vehicle time interval model, a communication delay model and a queue collision safety model are constructed; the inter-vehicle time interval, the communication delay coefficient and the safety coefficient are quantified into space particles, optimization is carried out based on a particle swarm algorithm, and the optimal inter-vehicle time interval on the basis of guaranteeing the queue safety and the fuel economy is obtained; designing a longitudinal model predictive control (MPC) expected acceleration decision controller of truck cooperative cruise by considering multi-target constraints of safety and fuel economy in a vehicle following process to obtain an expected acceleration; and a load change-considered feedforward and active-disturbance-rejection control brake driving error compensation model is established, so that the anti-jamming capability of the model is enhanced, and the actual acceleration of the queue truck accurately follows the expected acceleration under the load change condition.

The invention discloses a commercial vehicle cruise control method and system giving consideration to physiological strain and energy conservation. The method comprises the following steps that a human body physiological strain index is constructed, a vehicle oil consumption and energy conservation index is constructed, an optimal cruise speed planning model is established, and the vehicle oil consumption and energy conservation index and passing time are comprehensively considered to form an overall reward function; a reinforcement learning algorithm is introduced for solving, and the optimal cruise speed within the predicted duration is obtained; constructing a vehicle-seat-human body system longitudinal and vertical coupling dynamic model, and calculating a human body physiological strain index under the optimal cruise speed; vehicle state constraints and optimal cruise speed sequence tracking constraints are coded as control constraints, and a longitudinal model prediction control strategy is formed based on a human body physiological strain index, a vehicle fuel consumption energy-saving index and tracking deviation; and a pitching regulation and control mechanism is added to realize vertical ceiling hybrid control, and the vehicle suspension is regulated and controlled. The vehicle cruising performance can be improved, and collaborative optimization of human body physiological strain and vehicle energy saving is achieved.

This invention discloses a morphing control method for a conventional aircraft based on a disturbance observer. A longitudinal model of the aircraft is established, and variable parameters related to airfoil camber are introduced into the aerodynamic parameters. The relationship between the aircraft's aerodynamic parameters and airfoil camber is fitted, followed by small-disturbance linearization. Using the fitted functional relationship between the aircraft's longitudinal aerodynamic parameters and airfoil camber, a variable-parameter model of the aircraft is established, i.e., a specific state-space model. Based on the constructed state-space model, a disturbance observer is constructed to estimate disturbance dynamics. Combining the disturbance estimate and a PI-type state feedback controller, the controlled model is effectively controlled, improving stability. By combining the Lyapunov stability method and convex optimization methods, the controller gain and observer gain are calculated, thereby ensuring good dynamic performance of the controlled morphing aircraft system.

The present disclosure provides a method, device, storage medium and autonomous driving vehicle for longitudinal control of a vehicle, which relates to the field of computer technology, and more specifically to the field of artificial intelligence technology such as intelligent transportation and autonomous driving. The specific implementation scheme is as follows: when performing longitudinal control of the vehicle for autonomous driving, the predicted longitudinal speed of the vehicle at each predicted time point in the predicted time domain after the current moment is combined to determine the predicted longitudinal control parameters of the vehicle's model predictive controller at each predicted time point in the predicted time domain, and the longitudinal control amount at each predicted time point in the predicted time domain is determined in combination with the longitudinal control parameter information, the longitudinal model in the model predictive controller and the expected trajectory of the vehicle, and the longitudinal control amount at each predicted time point in the predicted time domain is also determined, and the longitudinal control of the vehicle is performed based on the longitudinal control amount at the first predicted time point in the predicted time domain. In this way, the accuracy and stability of the longitudinal control of the vehicle are improved, thereby improving the safety of the vehicle's autonomous driving.

The present invention discloses a finite-time formation fault-tolerant control method for fixed-wing unmanned aerial vehicles based on neural networks: First, consider using a virtual leader-follower structure for formation control, and adopt a distributed formation method for information interaction. Based on this, design a corresponding communication topology graph and calculate the corresponding adjacency matrix and Laplacian matrix; Then, for the longitudinal model of the fixed-wing unmanned aerial vehicle, simplify the dynamic model to a strict-feedback form based on reasonable assumptions, and consider the failure fault of elevator deflection; Based on the backstepping method and combined with sliding mode control, use a radial basis function neural network to process the unknown nonlinear functions of the model, and adopt an adaptive estimation of the failure fault of the elevator, so as to achieve finite-time fault-tolerant control. The present invention overcomes the problem that it is difficult to perform formation fault-tolerant control due to the longitudinal model of the fixed-wing unmanned aerial vehicle being a high-order nonlinear system, making the system have strong robustness and being able to stabilize within a finite time.

The present invention discloses a longitudinal model predictive control method for vehicles integrating long short-term memory network and Kalman filter. The steps include: establishing a vehicle longitudinal dynamics model considering the speed change of the leading vehicle as the prediction model of the MPC control framework; using the LTSM model to predict the acceleration value of the leading vehicle at each moment according to the historical acceleration of the leading vehicle and substituting it into the MPC control framework to calculate the corresponding control quantity; if the leading vehicle is an HDV, calculating the vehicle state estimation value at each moment, performing Kalman filter processing, and then substituting it into the MPC control framework; if the leading vehicle is a CAV, obtaining the actual value of the vehicle state in real time and substituting it into the MPC control framework; performing longitudinal control on the vehicle according to the control quantity of each control cycle. The present invention solves the problems of decreased control performance and poor stability of intelligent connected vehicles in the case of uncertainties in the environment and model parameters, and improves the vehicle operation efficiency while ensuring safety and comfort.

The invention discloses a vehicle speed decision-making method and system, a vehicle and equipment. The speed decision-making method of the vehicle comprises the following steps: determining a target obstacle according to a planned path of the vehicle; establishing a longitudinal model of the vehicle; performing forward simulation of the vehicle according to the state information of the vehicle and the state information of the target obstacle to obtain an input acceleration at a first moment; the input acceleration at the first moment is input into the longitudinal model, so that state variables of the vehicle at a second moment are obtained according to the input acceleration at the first moment and the position, speed, acceleration and jerk of the vehicle at the first moment, and the second moment is the next moment of the first moment; and determining a speed planning curve of the vehicle according to the obtained state variable of the vehicle. By adopting the method and the device, the state of the vehicle is updated by applying the vehicle longitudinal model, so that the lane forward simulation is closer to the real state of the kinematics of the vehicle, and the speed decision performance is improved.

This invention discloses a longitudinal anti-interference control method for a small fixed-wing unmanned aerial vehicle (UAV) based on the Actor-Critic framework. The steps are as follows: First, a longitudinal model of the UAV under disturbance is established; second, a performance function is designed to evaluate the control performance of the UAV, the Critic approximates the nonlinear performance function, and the Actor learns the optimal control law that minimizes the performance function; third, a disturbance neural network is added to estimate the disturbance of the UAV in the worst-case scenario, and a momentum neural network is used to improve the learning speed. This invention uses reinforcement learning technology and a neural network to approximate the performance function with the optimal control law, achieving adaptive control of the UAV under disturbance. This invention not only enhances the anti-interference capability of the UAV but also accelerates the convergence speed of the reinforcement learning control law.

The invention provides systems and methods for computing interpersonal compatibility using multi-modal data fusion that integrates genomic, immunologic, psychometric, biometric, contextual, and reproductive information. Genomic analysis includes variant calling, polygenic scoring, carrier-status evaluation, and HLA / KIR immune-compatibility modeling. Biometric inputs from wearable devices are processed to determine emotional synchrony and autonomic co-regulation. Psychometric and behavioral data are converted into latent-trait embeddings. A machine-learning fusion engine combines all modality-specific feature vectors to generate unified compatibility embeddings and dual outputs representing soulmate-stage suitability and family-planning compatibility. Additional embodiments include donor and surrogate matching, offspring-risk simulation, embryo-viability prediction, and longitudinal model refinement using real-world relational, biometric, or reproductive outcomes.

The invention provides a longitudinal control method and device of a vehicle, a storage medium and an automatic driving vehicle, and relates to the technical field of computers, in particular to the technical field of artificial intelligence such as the intelligent traffic field and the automatic driving technical field. According to the specific implementation scheme, when longitudinal control over automatic driving of a vehicle is carried out, predicted longitudinal control parameters of a model prediction controller of the vehicle at all prediction time points in a prediction time domain are determined in combination with predicted longitudinal speeds of the vehicle at all prediction time points in the prediction time domain after the current moment; and the longitudinal control parameter information is combined with a longitudinal model in the model prediction controller and the expected trajectory of the vehicle, the longitudinal control quantity at each prediction time point in the prediction time domain is determined, and the vehicle is longitudinally controlled based on the longitudinal control quantity at the first prediction time point in the prediction time domain. Therefore, the accuracy and stability of longitudinal control of the vehicle are improved, and then the safety of automatic driving of the vehicle is improved.

The invention provides a longitudinal control method and device of a vehicle, a storage medium and an automatic driving vehicle, and relates to the technical field of computers, in particular to the technical field of artificial intelligence such as the intelligent traffic field and the automatic driving technical field. According to the specific implementation scheme, when longitudinal control over automatic driving of a vehicle is carried out, predicted longitudinal control parameters of a model prediction controller of the vehicle at all prediction time points in a prediction time domain are determined in combination with predicted longitudinal speeds of the vehicle at all prediction time points in the prediction time domain after the current moment; and the longitudinal control parameter information is combined with a longitudinal model in the model prediction controller and the expected trajectory of the vehicle, the longitudinal control quantity at each prediction time point in the prediction time domain is determined, and the vehicle is longitudinally controlled based on the longitudinal control quantity at the first prediction time point in the prediction time domain. Therefore, the accuracy and stability of longitudinal control of the vehicle are improved, and then the safety of automatic driving of the vehicle is improved.

The present invention discloses a cruise control method and system for commercial vehicles that takes into account both physiological strain and energy conservation. The method includes the following steps: constructing a human physiological strain index, constructing a vehicle fuel consumption and energy conservation index, establishing an optimal cruise speed planning model, and comprehensively considering the vehicle fuel consumption and energy conservation index and travel time to form an overall reward function; introducing a reinforcement learning algorithm to solve and obtain the optimal cruise speed within the predicted time; constructing a longitudinal and vertical coupled dynamic model of the vehicle-seat-human system to calculate the human physiological strain index at the optimal cruise speed; encoding the vehicle state constraint and the optimal cruise speed sequence tracking constraint as control constraints, and forming a longitudinal model predictive control strategy based on the human physiological strain index, the vehicle fuel consumption and energy conservation index, and the tracking deviation; and adding a pitch control mechanism to realize vertical skyhook hybrid control and regulate the vehicle suspension. The present invention can improve vehicle cruise performance and achieve coordinated optimization of human physiological strain and vehicle energy conservation.

The application discloses a kind of intelligent decision support system and method based on longitudinal model conduction chain, belong to data processing system technical field, wherein, the system includes: model conduction engine, for building ordered model sequence, the output vector of each model in sequence as the input of subsequent model, form continuous decision conduction chain;Dynamic weight module, for realizing the weighted transmission of predecessor model output to subsequent model input by conduction matrix, the conduction matrix is based on model confidence error and dynamically adjusted;Closed-loop control unit, for monitoring the actual achievement situation of decision target, realizes the global optimization of longitudinal conduction chain by optimizing full-stack target function.By the application, it avoids the repeated processing of original data, realizes the ordered conduction of knowledge between models, improves the consistency, efficiency and robustness of decision.

The application discloses a kind of inclined shaft anisotropy has the fast calculation method of invasion stratum induction logging response, it is related to the technical field of electrical logging in oil exploration and development, comprising: constructing three-dimensional heterogeneous stratum model containing inclined shaft anisotropy invasion;Extracting invasion zone longitudinal model and original stratum longitudinal model;Considering induction logging instrument parameters, using semi-analytical algorithm and 0-dimensional inversion, obtain equivalent stratum model;Point by point construction radial heterogeneous model;In turn calculate the response of induction logging instrument different source distance and frequency operating mode, each mode response combination obtains induction logging synthetic apparent resistivity curve;Through all measurement depth points point by point cycle calculation, finally obtain the logging response of whole well section.The inclined shaft anisotropy has the hierarchical superposition of stratum decomposition for invasion, by combining semi-analytical solution and neural network algorithm, induction logging response calculation speed is improved more than three orders of magnitude.

The invention discloses an intelligent decision support system and method based on a longitudinal model conduction chain, and belongs to the technical field of data processing systems, and the system comprises a model conduction engine which is used for constructing an ordered model sequence, taking the output vector of each model in the sequence as the input of a subsequent model, and forming a continuous decision conduction chain; the dynamic weight module is used for realizing weighted transmission from the output of the precursor model to the input of the subsequent model through a conduction matrix, and the conduction matrix is dynamically adjusted based on a model confidence error; and the closed-loop control unit is used for monitoring the actual achievement condition of the decision target and realizing global optimization of the longitudinal conduction chain by optimizing a full-stack target function. Through the method and the device, repeated processing of original data is avoided, ordered conduction of knowledge among models is realized, and consistency, efficiency and robustness of decision making are improved.

The invention discloses a dangerous driver longitudinal model construction method based on Levy random characteristics. The method comprises the following steps: firstly, collecting vehicle mass driving data in an actual road traffic environment, deriving driving intensity by using a driving condition Markov state equation, fitting the driving intensity by using Levy distribution, and generating a driving intensity random sample; secondly, calculating a driving intensity boundary of the current acceleration, finding an index of a driving intensity random sample at the boundary, reserving a long tail value of the index to ensure a rapid transfer path of a large and small step length of the driving intensity, randomly selecting the long tail value as the driving intensity at the current moment, obtaining the acceleration at the next moment, constraining the acceleration and calculating the speed at the next moment; and finally, updating the current speed and the current acceleration, and judging whether the maximum duration is reached or collision occurs or not until a dangerous longitudinal driving behavior sequence is output. According to the method, the random dangerous driver longitudinal behavior can be quickly generated, and a reference is provided for simulation test of an accelerated automatic driving longitudinal auxiliary driving system.

A method for safe platooning of multiple vehicles on roads based on model predictive control includes: establishing a discrete kinematic model of multiple vehicles considering vehicle spacing constraints and sideslip disturbances; designing a longitudinal model predictive controller based on the model, introducing a one-sided hinge function and time-varying weights to construct an asymmetric vehicle spacing penalty term in the cost function, and adding vehicle spacing and velocity / acceleration boundary constraints in rolling optimization to obtain longitudinal control quantities; designing a nonlinear extended state observer to estimate sideslip disturbances online; designing an integral sliding mode controller based on lateral tracking error, and combining a nonlinear fal(·) function to suppress chattering and output steering control quantities; this invention solves the problems of insufficient safety margin, decreased coordination accuracy, and lateral control chattering that easily occur in multi-vehicle platooning under strict vehicle spacing constraints and sideslip disturbances on curved roads, improves safe platooning capability under vehicle spacing constraints, enhances steering accuracy and trajectory tracking robustness on curved roads, and improves the smoothness of control commands.

The invention discloses a rapid calculation method for the induction logging response of an anisotropic invasion stratum of an inclined shaft, and relates to the technical field of oil exploration and development electrical logging, and the method comprises the steps: constructing a three-dimensional heterogeneous stratum model containing anisotropic invasion of the inclined shaft; extracting an intrusive zone longitudinal model and an undisturbed stratum longitudinal model; an equivalent stratum model is obtained by considering parameters of an induction logging instrument and utilizing a semi-analytical algorithm and 0-dimensional inversion; constructing a radial heterogeneous model point by point; the responses of the induction logging instrument in different source spacing and frequency working modes are calculated in sequence, and all the mode responses are combined to obtain an induction logging synthetic apparent resistivity curve; and through point-by-point circulation calculation of all the measurement depth points, the logging response of the whole well section is finally obtained. According to the method, the anisotropic invaded stratum of the inclined shaft is decomposed into graded superposition of longitudinal heterogeneous and radial heterogeneous influences, and the induction logging response calculation speed is increased by more than three orders of magnitude by combining algorithms such as a semi-analytical solution and a neural network.