检索结果-内蒙古大学图书馆

Two-Stage Game Guidance Strategy With Impact Point for Active Defense Aircraft in Two-on-Two Engagement

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC systEMS 2025年第1期61卷 710-729页

作者： Wang, Xintao Yang, Ming Wang, Songyan Chao, Tao Harbin Inst Technol Control & Simulat Ctr Natl Key Lab Modeling & Simulat Complex Syst Harbin 150001 Peoples R China

A two-stage game guidance strategy is designed in this article using the optimal control method in a two-on-two engagement scenario, which consists of a defender (low-value aircraft), a target (high-value aircraft), and two attackers. The probability of the attackers intercepting the target is assumed to devise an impact point in the engagement. The greater the probability, the closer the impact point is to the attacker. Therefore, the engagement is divided by the impact point into two stages. The first stage is a three-player confrontation between the defender, the target, and the impact point, where the defender remains on the line-of-sight between the target and the impact point. The defender is closer to the attacker by pursuing the impact point to increase the success rate of combat. For the second stage, the defender intercepts the attacker posing the greatest threat to the target at the desired terminal angle while the target adopts an optimal avoidance strategy. simulations are performed to verify the effectiveness and feasibility of the guidance strategy.

关键词： IP networks Aircraft Optimal control Games Differential games Chaos Aerospace control Active defense aircraft guidance strategy impact point (IP) keywords optimal control two-stage guidance

来源：评论

学校读者我要写书评

暂无评论

An intelligent model selection method based on graph representation learning

引用

simulatION-TRANSACTIONS OF THE SOCIETY FOR modeling AND simulatION INTERNATIONAL 2025年第4期101卷 493-505页

作者： Yang, Fan Ma, Ping Li, Wei Yang, Ming Harbin Inst Technol Control & Simulat Ctr POB 3006Sci Pk Harbin 150080 Peoples R China Natl Key Lab Complex Syst Modeling & Simulat Harbin Peoples R China

To select the most credible simulation model among multiple alternatives with dynamic and correlated outputs, an intelligent model selection method based on graph representation learning (GRL) is proposed, which treats the model selection problem as a reference data categorization problem. To model the correlations between the output variables, the evaluation data are initially transformed from their traditional two-dimensional format into a graph-structured format based on the distance correlation coefficients. Then, graph isomorphism networks (GINs) are employed to achieve GRL and evaluation data classification. The graph embeddings produced by GRL, which represent the interdependencies and dynamic evolutionary patterns among variables, enable the categorization of reference data as originating from one of the alternative models. Finally, the most credible simulation model is determined based on the category probabilities of the multisample reference data. The effectiveness of the proposed method in feature extraction and model selection is demonstrated through an application example on aerodynamic parameter models of a flight vehicle.

关键词： Model selection dynamic and correlated outputs graph neural network graph representation learning data categorization

来源：评论

学校读者我要写书评

暂无评论

Real-Time Dynamic Visual-Inertial SLAM and Object Tracking Based on Lightweight Deep Feature Extraction Matching

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Zhang, Hanxuan Huo, Ju Huang, Yulong Liu, Qi Harbin Inst Technol Natl Key Lab Modeling & Simulat Complex Syst Harbin 150001 Peoples R China Harbin Engn Univ Coll Intelligent Syst Sci & Engn Harbin 150001 Peoples R China

To mitigate the heavy reliance on semantic information and the unreliability of manual feature extraction in dynamic simultaneous localization and mapping (SLAM) and object tracking systems, a novel visual-inertial SLAM with deep feature extraction matching is proposed. A lightweight network is designed for feature extraction and description, replacing the oriented FAST and rotated BRIEF (ORB) approach, which can address deep learning latency and the shortcomings of manual extraction. A fast object tracking method is developed for extracting and associating dynamic objects based on clustering analyses of feature point pair distances to epipolar lines, which enables real-time tracking of numerous objects without semantic data. An advanced online incremental loop closure detector for deep features is designed, which supersedes ORB-based detectors and maintains global pose optimization. The system's effectiveness and advantages, including its proficiency in real-time embedded platform execution and enhanced self-localization and dynamic object tracking, have been demonstrated through extensive evaluations. Notably, the system is capable of consistently tracking dynamic objects with rapid movement or weak texture, furnishing the localization system with robust dynamic constraints.

关键词： Feature extraction Dynamics Simultaneous localization and mapping Real-time systems Object tracking Vehicle dynamics Location awareness Semantics Data mining Accuracy Deep feature extraction matching dynamic visual-inertial simultaneous localization and mapping (SLAM) loop closure detection multiple object tracking self-location

来源：评论

学校读者我要写书评

暂无评论

MDOFusion: A visible and infrared image fusion method based on multi-dimensional quantification allocation and dual optimization mechanism

引用

EXPERT systEMS WITH APPLICATIONS 2025年 280卷

作者： Liu, Tao Chen, Bo Wang, Benkuan Liu, Datong Harbin Inst Technol Sch Elect & Informat Engn Harbin 150080 Peoples R China Harbin Inst Technol Natl Key Lab Modeling & Simulat Complex Syst Harbin 150080 Peoples R China

Visible and infrared image fusion can compensate for imaging defects of visible and infrared images and obtain fusion results with rich textures and significant features, which is widely used in advanced visual tasks. Many existing image fusion methods focus on improving the fusion performance in low-light conditions with texture degradation. However, these methods are prone to cross-modality feature interference and information loss when faced with complex image quality degradation situations such as overexposure, low texture, and blur, limiting their broader applications. To cope with these challenges, a fusion method based on multi-dimensional quantification allocation and dual optimization mechanism is proposed, termed MDOFusion. Firstly, a multidimensional quantification allocation mechanism is designed to allocate fusion weights based on quantification and multi-information decision-making, so that the fusion weights can be adaptively adjusted according to the quality degradation of source images, thereby avoiding the imbalanced heterogeneous information to affect visual effects. Then, the obtained adaptive weight factors are embedded in the dual optimization mechanism, where a cross-modality enhancement fusion (CMEF) block is designed to optimize the combination of heterogeneous information, and weight-guided loss functions are designed to reduce information loss. Experiments on RoadScene, MSRS, and DroneVehicle datasets show that the fusion results of MDOFusion have reasonable color distribution and rich visual information, and achieve superior results in comparative experiments.

关键词： Image fusion Quality degradation Multi-dimensional quantification allocation Dual optimization mechanism Multi-layer feature attention

来源：评论

学校读者我要写书评

暂无评论

Constrained dynamic control allocation based on frequency characteristics of actuators for attitude control systems with parametric uncertainties

引用

AIRCRAFT ENGINEERING AND AEROSPACE TECHNOLOGY 2025年第4期97卷 498-509页

作者： Jing, Hongyu Ma, Kemao Harbin Inst Technol Control & Simulat Ctr Natl Key Lab Complex Syst Control & Intelligent Ag Harbin Peoples R China

PurposeIn pursuit of higher maneuverability and aerodynamic characteristics, aerodynamic configuration for an attitude control system of aircraft adopts generally an over-actuated form. The purpose of this paper is to address allocation problems of multiple actuators to improve the system rapidity and performance and simultaneously solve parameter uncertainties of the aircraft attitude control ***/methodology/approachTaking into account the respective frequency characteristics of actuators as well as position and rate constraints, the proposed method extends regular quadratic-programming control allocation by using a dynamic weighting matrix. And a robust controller, issuing a virtual control command to be allocated, is designed based on H infinity mixed sensitivity *** an attitude control system with parametric uncertainties, the proposed virtual robust controller and control allocation method is verified and the system performance is ***/valueThe proposed dynamic control allocation method is designed based on actuator dynamic characteristics and the changing rate of the virtual control command, considering some actuator constraints simultaneously. The efficiency of the attitude control system is improved and the complex multi-input and multi-output system model can be simplified.

关键词： Dynamic control allocation Actuator frequency characteristics Quadratic programming Mixed sensitivity robust control Aircraft attitude control

来源：评论

学校读者我要写书评

暂无评论

The Optimization of Space-Filling and Orthogonality for Latin Hypercube Design Using a Local Search-Based NSGA-II

引用

JOURNAL OF STATISTICAL THEORY AND PRACTICE 2025年第1期19卷 1-26页

作者： Hu, Xiaoru Ma, Ping Li, Shuang Li, Wei Yang, Ming Harbin Inst Technol Control & Simulat Ctr Harbin 150000 Peoples R China Natl Key Lab Modeling & Simulat Complex Syst Harbin 150000 Peoples R China

Latin hypercube design (LHD), as a stratified sampling method, is widely employed in the design of experiments. To improve the space-filling and orthogonality of LHD, this paper proposes an efficient multi-objective optimization method, denoted as local search-based non-dominated sorting genetic algorithm II (LSNSGA-II). Compared with the vanilla non-dominated sorting genetic algorithm II (NSGA-II), LSNSGA-II utilizes a full-factors-based simulated binary crossover operator and a local search strategy to enhance its search ability. Furthermore, a cyclic elimination strategy in the elitist selection phase is also adopted to augment the uniformity of the Pareto fronts. Comparative experiments were conducted against various LHDs with different dimensions and numbers of sampling points, and the results demonstrate that the proposed LSNSGA-II significantly outperforms other peer algorithms from the perspectives of Hypervolume metric and computational efficiency, particularly suitable for high-dimensional and low-sampling scenarios.

关键词： Latin hypercube design Space-filling Orthogonality Multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

Perception-Aware Based Quadrotor Translation and Yaw Angle Planner in Unpredictable Dynamic Situations

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC systEMS 2025年第1期61卷 47-60页

作者： Zhang, Hanxuan Huo, Ju Huang, Yulong Wang, Dingyi Harbin Inst Technol Harbin 150001 Peoples R China Natl Key Lab Modeling & Simulat Complex Syst Harbin 150001 Peoples R China Harbin Engn Univ Coll Intelligent Syst Sci & Engn Harbin 150001 Peoples R China

In this article, we offer a perception-aware quadrotor translation and yaw angle planner approach to solve the navigation problem for a quadrotor with limited field of view (FOV) in unpredictable dynamic situations. Our method is developed based on the static obstacle avoidance method Ego-Planner. First, we establish an environmental perception module based on a depth sensor. This module categorizes obstacles into static and dynamic types, tracking and predicting the trajectories of dynamic obstacles. Second, we introduce the minimum volume enclosing polynomial curves basis instead of B-spline basis to solve the problem of conservative convex hull generated by existing planning methods based on B-spline basis. To enable dynamic obstacle avoidance, we design a method that combines modified kinematic path searching with gradient optimization, avoiding the need for maintaining a Euclidean signed distance field that adds computational burden in existing approaches. Finally, we jointly optimize translational motion, yaw angle rotation, and the visibility cost of tracking obstacles in the FOV to maximize the unmanned aerial vehicle's ability to observe unknown obstacles early and evade them promptly. simulation experiments demonstrate that in unpredictable dynamic situations, our proposed planner can effectively avoid obstacles, achieving a high success rate of up to 93%.

关键词： Aerodynamics Trajectory Vehicle dynamics Planning Autonomous aerial vehicles Quadrotors Optimization Minimum volume enclosing polynomial curves (MINVO) perception-aware (PA) translation planner unpredictable dynamic situations yaw angle planner

来源：评论

学校读者我要写书评

暂无评论

SWIPT-Enabled Full-Duplex Short Packet Communications With Nonlinear Energy Harvesting

引用

INTERNATIONAL JOURNAL OF DISTRIBUTED SENSOR NETWORKS 2025年第1期2025卷

作者： Chen, Dechuan Li, Jin Hu, Jianwei Zhang, Xingang Zhang, Shuai Wang, Dong Nanyang Normal Univ Coll Phys & Elect Engn Nanyang Henan Peoples R China Natl Key Lab Complex Syst Simulat Beijing Peoples R China

In this work, we examine a simultaneous wireless information and power transfer (SWIPT)-enabled full-duplex (FD) short packet communication system in which both users are equipped with a pair of transmitter-receiver antennas and can transmit and receive simultaneously. Specifically, an energy-constrained user employs the power splitting protocol to harvest the energy of radio frequency signals transmitted by another user. To assess the reliable performance of the system, we consider two practical situations, that is, independent uplink and downlink, as well as identical uplink and downlink. For both scenarios, we derive closed-form approximations for the overall block error rate (BLER), taking into account the influence of finite blocklength codes and nonlinear energy harvesting model. Subsequently, we analyze the effective throughput to characterize the efficiency of the considered system. Our simulation and numerical results confirm the accuracy of the theoretical approximations and demonstrate that there exists an optimal transmit power to minimize the overall BLER.

关键词： effective throughput FD overall BLER short packet communication SWIPT

来源：评论

学校读者我要写书评

暂无评论

Perception-Aware-Based UAV Trajectory Planner via Generative Adversarial Self-Imitation Learning From Demonstrations

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第3期12卷 3248-3260页

作者： Zhang, Hanxuan Huo, Ju Huang, Yulong Cheng, Jiajun Li, Xiaofeng Harbin Inst Technol Sch Elect Engn & Automat Harbin 150001 Peoples R China Natl Key Lab Modeling & Simulat Complex Syst Harbin 150001 Peoples R China Harbin Engn Univ Coll Intelligent Syst Sci & Engn Harbin 150001 Peoples R China

The use of unmanned aerial vehicles (UAVs) for Internet of Things applications, like intelligent monitoring and search, is increasingly becoming a popular research focus globally. While various optimization algorithms exist to plan UAV flight paths, they frequently compromise the quality of the planning path to decrease planning time. In view of the above problems, a perception-aware-based UAV trajectory planner via generative adversarial self-imitation learning from demonstration is proposed. First, a progressively growing discriminator is devised to prevent the policy network from being overpowered in early training stages, avoiding potential training failures. Second, the issue of homogenized strategic patterns among optimized expert trajectories is solved by incorporating successful trajectories from the policy network into the expert buffer, which thereby enhances the network's generalization capabilities. Third, to address the challenges of skewed distribution and considerable performance variation among the strategies learned by the policy network during training, a class-level instance-balancing expert buffer is introduced. Finally, the yaw angle of the UAV in real time during flight is obtained by using the analytical solution of the position trajectory and yaw angle and the position trajectory output from the policy network. Experiments confirm our proposed method achieves comparable flight costs and success rates to those of the reference expert method, while the planning time is reduced. The proposed method is also shown to be well adapted to dynamic environments and obstacle trajectories, which are not involved in training. Additionally, the ablation studies highlight the individual contributions of each component within the proposed method.

关键词： Trajectory Autonomous aerial vehicles Trajectory planning Planning Training Imitation learning Real-time systems Internet of Things Robustness Costs Class-level instance-balancing generative adversarial self-imitation learning from demonstration (GASILFD) perception-aware-based trajectory planning progressively growing discriminator unmanned aerial vehicle (UAV)

来源：评论

学校读者我要写书评

暂无评论

Opinion diversity shaped by higher-order interactions on multi-dimensional issues

引用

CHAOS SOLITONS & FRACTALS 2025年 194卷

作者： Qi, Yimeng Xue, Dong Liu, Fangzhou Harbin Inst Technol Res Inst Intelligent Control & Syst Harbin 150001 Peoples R China East China Univ Sci & Technol Key Lab Smart Mfg Energy Chem Proc Minist Educ Shanghai 200237 Peoples R China Harbin Inst Technol Natl Key Lab Modeling & Simulat Complex Syst Harbin 150001 Peoples R China

Existing opinion dynamics models on consensus phenomena cannot fully account for the diversity of opinions observed in real-world societies. Interpersonal interactions often occur in higher-order combinations, whereby dyadic interactions are modulated by the states of individuals or groups. In this study, a new framework is investigated to model opinion dynamics in higher-order networks with multidimensional issues, addressing the limitations of existing models that primarily focus on pairwise interactions and scalar opinions. By extending the Friedkin-Johnsen (FJ) model to incorporate higher-order interactions, nonlinear dynamics are introduced to more accurately capture the nuanced behavior of real social systems. The theoretical and numerical results demonstrate that higher-order terms promote amore diverse distribution of opinions, reflecting the coexistence of multiple stances. Furthermore, we highlight the critical interplay between individual stubbornness and social influence in shaping consensus and opinion diversity. These findings advance the understanding of how higher-order interactions impact the long-term evolution of opinions in complex social systems.

关键词： Higher-order networks Opinion dynamics Multi-dimensional issues Opinion diversity

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：