Abstract In recent years, along with the rapid development in domain of artificial intelligence and aerospace, aerospace combined is future trend. As an important basic tool for Natural Language Processing, Named Entity Recognition technology can help obtain key relevant knowledge from a large number data. this paper, we produced entity recognition dataset containing 30 k sentences Chinese developed named model that Multi-Feature Fusion Transformer (MFT), which combines features such as...

In this article, the nonzero-sum pursuit-evasion (PE) game control problem is studied for a class of linear spacecraft systems subject to complete information case and incomplete case. The includes cost functions inputs. practical confrontation situations, due constraints, it impossible pursuer evader build up exact opposite function. Hence, framework utilized describe PE double-spacecraft system. First all, under case, strategy designed by solving coupled Riccati recursions. Then, aiming at...

This paper puts forward a coordinated formation control scheme for multiple fixed-wing unmanned aerial vehicle (UAV) systems with external nonlinear disturbances including not only the drag force and uncertain lateral force, but also drag, lift, forces caused by wake vortices. A novel distributed finite-time extended state observer is designed to estimate both unmeasurable states of each UAV. In particular, an event-triggered mechanism employed reduce burden communication networks among...

Abstract Voltage sags are one of the primary factors in power quality issues that lead to losses for sensitive users and reduce operation resilience distribution networks. However, due lack accessibility users’ production information, accurately quantifying networks under impact voltage is challenging. In this letter, first an index using a trapezoidal curve defined. Considering varying tolerance levels sags, feature indices system established adaptive S ‐transform, sample dataset generated...

Over the past decade, information for precision disease medicine has accumulated in form of textual data. To effectively utilize this expanding medical text, we proposed a multi-task learning-based framework based on hard parameter sharing knowledge graph construction (MKG), and then used it to automatically extract gastric cancer (GC)-related biomedical from literature identify GC drug candidates. In MKG, designed three separate modules, MT-BGIPN, MT-SGTF MT-ScBERT, entity recognition,...

In this work, we develop a trajectory tracking control method for unmanned surface vessels (USVs) based on real-time compensation actual wave disturbances. Firstly, information from the sea is extracted through stereoscopic visual observations, and data preprocessing performed using task-driven point cloud downsampling network. We reconstruct phase-resolved field in real time. Subsequently, disturbances are modeled mechanically, used as feedforward inputs. Furthermore, an adaptive...

In this paper, we explore the problem of smooth braking at preset points in autonomous vehicles using model predictive control (MPC) with a receding horizon extended state observer (RHESO) and neural network (NN). An NN-based modeling method is proposed to intuitively describe relationship between vehicle speed controllers (brake throttle), establish dynamic vehicles. A sufficient condition put forward guarantee convergence NN. Furthermore, composite MPC strategy based on RHESO designed,...

Utility harmonic impedance is an important parameter for mitigation. In this paper, a method utility estimation based on constrained independent component analysis proposed. The conventional ComplexICA has two major problems: the algorithm not suitable separating weak and strong source mixed signals, lots of sample data should be provided to avoid converging local optimum. To solve problems, prior information added objective function ComplexICA; in measurement at PCC when load shutdown are...

Aiming at de-tumbling a non-cooperative space target safely and efficiently, an eddy brake approach utilizing multiple high-temperature superconducting (HTS) coils is proposed in this paper. The configuration design criteria of HTS coil are constructed first to guarantee the validity method. Then, considering that each mounted on servicing satellite, desired position attitude satellite calculated meet criteria. Next, process analyzed, where how generate keep magnetic field considered, then...

A model-free control method is applied to the attitude and orbital operation of post-capture combined spacecraft, which consists a space robot debris. The main contribution this paper lies in following three aspects. Firstly, discrete dynamic linearization motion equation for spacecraft proposed, then, standardized expression form multiple input output system dynamics motions are presented. Secondly, data mapping model defined, based on this, an initial value online optimization provided,...

In order to achieve a straight ballistic trajectory of missile and reduce the update frequency normal acceleration for interception maneuvering target, backstepping-based parallel approaching guidance method is designed with nonlinear disturbance observer (NDO) technique event-triggered (ET) mechanism in this paper. suppress adverse effect target maneuver, NDO estimate acceleration. Then, NDO-based backstepping used obtain realize guidance. acceleration, ET employed method. If relatively...