Most Download

Published in last 1 year| In last 2 years| In last 3 years| All| Most Downloaded in Recent Month | Most Downloaded in Recent Year|

Published in last 1 year

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Estimation of the Berthing Parameter of Unmanned Surface Vessels Based on 3D LiDAR Wang Haichao, Yin Yong, Jing Qianfeng, Cong Lin Journal of System Simulation    2024, 36 (8): 1737-1748.   DOI: 10.16182/j.issn1004731x.joss.24-0262 Abstract （6733）   HTML （2540）    PDF（pc） （4470KB）（2526）       Knowledge map    Save Accurate estimation of berthing parameters is a prerequisite for unmanned surface vessel autonomous berthing. A method for berthing parameter estimation is proposed based on shipborne 3D LiDAR. The method consists of two main modules: ship pose estimation and berthing state estimation. In the berthing position estimation module, raw point cloud data undergoes preprocessing algorithms aims at downsampling and removing outliers. Point cloud registration algorithms are employed to determine the vessel's position during the berthing process. The berthing state estimation module extracts berth boundary information by using the MSAC algorithm, and on the basis of this information, calculates the berthing parameters. Experimental analysis results show that the ship pose information and berthing parameter information obtained by the algorithm are consistent with reality. The average berthing distance error is less than 0.023 m, and the average angle error is less than 0.26°, which verifies the accuracy and rationality of this berthing parameter estimation algorithm. Table and Figures | Reference | Related Articles | Metrics

Select

Thinking of Aerospace Equipment Systematization Simulation Technology Development Bao Weimin, Qi Zhenqiang Journal of System Simulation    2024, 36 (6): 1257-1272.   DOI: 10.16182/j.issn1004731x.joss.24-0548 Abstract （2798）   HTML （957）    PDF（pc） （6596KB）（2313）       Knowledge map    Save The aerospace field is flourishing in the new era. Aerospace equipment presents new characteristics such as systematization, new quality, high efficiency and intelligence. Simulation technology plays a more important role in the digital aerospace era as a means of enhancing efficiency and empowerment covering all stages of the entire lifecycle, including project demonstration, research and development, testing, manufacturing, training, and maintenance. The conception of aerospace equipment systematization simulation technology is introduced, the current development status and practices at home and abroad are elaborated, and the future development trends and challenges of aerospace equipment systematization simulation technology are evaluated. Focusing on the systematic development of aerospace simulation technology, on the basis of key breakthroughs and evolving promotion, the development ideas are proposed from the dimensions of technical system, supporting applications, and utility evolution. The contribution of the emerging hotspots such as artificial intelligence, big data, virtual reality, and digital technology to the development of aerospace equipment systematization simulation is discussed. Table and Figures | Reference | Related Articles | Metrics

Select

UAV Path Planning Based on Improved Harris Hawk Algorithm and B-spline Curve Huang Zhifeng, Liu Yuanhua Journal of System Simulation    2024, 36 (7): 1509-1524.   DOI: 10.16182/j.issn1004731x.joss.23-0403 Abstract （5681）   HTML （2264）    PDF（pc） （6057KB）（2305）       Knowledge map    Save Aiming at the global path planning problem of unmanned aerial vehicles (UAVs) in dynamic environments, this paper proposes an improved Harris Hawk optimization algorithm. To address the problem of insufficient search performance in the later stage of the algorithm, an adaptive chaos and core population dynamic partitioning strategy is proposed to improve the searchability of the algorithm in the later stage. The Harris Hawk update formula is modified, and the golden sine strategy is introduced to improve the search efficiency of the algorithm. Then, an adaptive dynamic cloud optimal solution perturbation strategy is integrated to improve the ability of the algorithm to jump out of the local extremum. For the three-dimensional grid path planning problem, a valuation function is established. By calculating the cost of reaching the endpoint for each grid, the algorithm is aided in filtering nodes, allowing it to search for a shorter path. For the problem of the non-smooth path, the path angle is processed by using the cubic B-spline curvefor three times to make the path more suitable for UAV flight. The effectiveness of the improved algorithm is validated by simulation experiments on international standard test functions and static and dynamic grid maps of varying sizes and complexity. The experimental results demonstrate that the proposed algorithm significantly outperforms the control group algorithm. On average, the planned path is shortened by 14.94% and the number of corners is reduced by 53.31%. Table and Figures | Reference | Related Articles | Metrics

Select

Digital Twin Modeling and Control of Robots for Intelligent Manufacturing Scenarios Li Ying, Gao Lan, Zhu Zhisong Journal of System Simulation    2024, 36 (7): 1536-1545.   DOI: 10.16182/j.issn1004731x.joss.23-0481 Abstract （4033）   HTML （290）    PDF（pc） （5342KB）（1331）       Knowledge map    Save The introduction of Industry 4.0 and the Made in China 2025 development policy has accelerated the transformation of the manufacturing industry from automation to intelligence. Industrial robots, as the representative equipment of intelligent manufacturing, will also become more intelligent. Based on digital twin technology, digital modeling, and simulation debugging are conducted for such problems as interference and collision, tedious operation, and low efficiency of industrial robot spot welding debugging in production. Process Simulate from TECNOMATIX software is utilized to digitally model the robot spot welding station and define its motion, and TIA Portal and S7-PLCSIM Advanced are applied to build a virtual simulation and commissioning environment to realize multi-robot cooperative work at the processing station controlled by an external virtual PLC. The simulation results show that the robot can reach all working points during the motion and the joint speed is always kept within a reasonable range, which meets the requirements of safety and stability in the actual production process. At the same time, the robot spot welding station simulation by digital twin technology can find product defects in time, shorten the debugging cycle, and reduce the cost. Table and Figures | Reference | Related Articles | Metrics

Select

Research on Simulation Resource Management Based on Graph Association Organization Liu Zewei, Ding Yishan, Lin Tingyu, Ke Mingxing, Guo Liqing, Xiao Yingying, Zhao Zhilong, Li Yan, xuan Lü Journal of System Simulation    2024, 36 (9): 1983-1994.   DOI: 10.16182/j.issn1004731x.joss.24-0455 Abstract （2843）   HTML （991）    PDF（pc） （1689KB）（1023）       Knowledge map    Save The simulation test and evaluation of intelligent system of systems, systems and single equipment is a complex system engineering, which requires effective management of multi-source, heterogeneous and distributed massive simulation resources scattered in cloud test centers and test sites of various units; and good control of dynamically generated tasks, assumptions, configurations, results, evaluations and other data and files. The traditional way of managing and querying simulation resources by category is inefficient and difficult to meet the requirements of large-scale intelligent simulation test and evaluation activities. An overall framework for simulation resource management based on graph association organization, defines a simulation resource association organization metamodel for graph association organization, and proposes key algorithms and methods for dynamically extracting simulation resource information managed in different tools/systems, constructs a simulation resource graph structure based on association organization, and provides on-demand access to simulation resources. Verified by application examples, this method can accurately mark the state changes of simulation resource sets that can affect the simulation operation results during the intelligent evolution process, and effectively improve the efficiency of simulation resource management and retrieval. Table and Figures | Reference | Related Articles | Metrics

Select

AGV Scheduling Problem at Automated Terminals Based on Improved DQN Algorithm Liang Chengji, Zhang Shidong, Wang Yu, Lu Bin Journal of System Simulation    2024, 36 (11): 2592-2603.   DOI: 10.16182/j.issn1004731x.joss.23-0912 Abstract （390）   HTML （14）    PDF（pc） （3531KB）（993）       Knowledge map    Save A future tasks considering deep Q-network (F-DQN) algorithm was proposed to output real-time scheduling results of automated guided vehicles (AGVs) at automated terminals. This algorithm combined the advantages of real-time scheduling and static scheduling, improving the system status by considering static future task information when making real-time decisions, so as to obtain a better scheduling solution. In this study, the actual layout and equipment conditions of the Yangshan phase IV automated terminal were considered, and a series of simulation experiments were conducted using the Plant Simulation software. The experimental results show that the F-DQN algorithm can effectively solve the real-time scheduling problem of AGVs at automated terminals. Furthermore, the F-DQN algorithm significantly reduces the waiting time of quay cranes compared to the traditional DQN algorithm. Table and Figures | Reference | Related Articles | Metrics

Select

Adaptive PID Control Algorithm Based on PPO Zhou Zhiyong, Mo Fei, Zhao Kai, Hao Yunbo, Qian Yufeng Journal of System Simulation    2024, 36 (6): 1425-1432.   DOI: 10.16182/j.issn1004731x.joss.23-0137 Abstract （490）   HTML （13）    PDF（pc） （2022KB）（813）       Knowledge map    Save A six-axis robotic arm is built and simulated in a complex control environment with disturbances by using MATLAB physics engine and Python, which provides a trial-and-error environment for the robotic arm training that could not be provided in reality. Proximal policy optimization(PPO) algorithm in reinforcement learning is proposed to improve the traditional PID control algorithm. By introducing the multi-agent idea and on the basis of the different effects of the three parameters of PID on control system and the characteristics of the six-axis robotic arm, the three parameters are separately trained as different intelligent individuals to achieve a new multi-agent adaptive PID algorithm with multi-agent adaptive adjustment of parameters. Simulation results show that the algorithm outperforms MA-DDPG and MA-SAC algorithms in training convergence. Compared with the traditional PID algorithm, the algorithm can effectively suppress the disturbances and oscillations, and has lower overshoot and adjustment time, which makes the control process smoother and effectively improves the control accuracy of the robotic arm. The robustness and effectiveness is proved. Table and Figures | Reference | Related Articles | Metrics

Select

A Plugin-based Unreal Engine Adapter for HLA-based Distributed Simulation Yang Mei, Wang Peng Journal of System Simulation    2024, 36 (10): 2231-2237.   DOI: 10.16182/j.issn1004731x.joss.24-0872 Abstract （1579）   HTML （574）    PDF（pc） （846KB）（803）       Knowledge map    Save With the wide application of game engine-based simulation in transportation, military and other fields, the demand for interoperability between game engine and traditional simulations is becoming increasingly strong. For the HLA-based integration of Unreal Engine and the traditional simulations, a plugin-based Unreal Engine adapter for distributed simulation is designed, which enables the rapid development of Unreal Engine federate and the efficient integration. The simulation shows the feasibility of the plugin-based Unreal Engine adapter. Table and Figures | Reference | Related Articles | Metrics

Select

Dynamic Data Driven Simulation: An Overview Xie Xu, Qiu Xiaogang, Bao Yizheng, Xu Kai Journal of System Simulation    2024, 36 (8): 1832-1842.   DOI: 10.16182/j.issn1004731x.joss.24-0127 Abstract （581）   HTML （18）    PDF（pc） （673KB）（789）       Knowledge map    Save Dynamic data driven simulation is a simulation paradigm which integrates simulation and data together. This paradigm continuously feeds real-time data into the simulation, enabling the simulation be dynamically adjusted by the data, which thus improves the simulation-based estimation and prediction capability. Due to this integration, the dynamic data driven simulation can estimate system states and predict future state evolution more accurately. This paper reviews the origins and basic concept of dynamic data driven simulation, and introduces several simulation paradigms originated from the idea of "integrating models with data", and identifies the linkages and differences among them. The particle filter-based data assimilation method and the identical-twin simulation experiment are introduced. The current research status of dynamic data driven simulation is summarized from four perspectives, i.e., application scenarios, models and data, data assimilation algorithms, and integration with new technologies. Finally, the future research directions are outlooked from five aspects, which are simulation models, measurement data, data assimilation, algorithm performance, and application areas. Table and Figures | Reference | Related Articles | Metrics

Select

Improving NSGA-III Algorithm for Solving High-dimensional Many-objective Green Flexible Job Shop Scheduling Problem Xu Yigang, Chen Yong, Wang Chen, Peng Yunxian Journal of System Simulation    2024, 36 (10): 2314-2329.   DOI: 10.16182/j.issn1004731x.joss.23-0694 Abstract （268）   HTML （4）    PDF（pc） （2792KB）（680）       Knowledge map    Save Aiming at the poor initial solution quality and low local search efficiency of NSGA-III in solving the many-objective flexible job shop scheduling model, an improved NSGA-III (NSGA-III-TV) is proposed. Based on MSOS encoding, the different mixed initialization strategies are adopted for OS and MS chromosomes to improve the quality of initial solutions. Based on the critical path, an improved N6 neighborhood structure is used for neighborhood search, which effectively reduce the completion time and reducing search randomness. Three effective mutation operators are employed to expand the search space and improve the convergence capability in the later stages. Test results show that NSGA-III-TV has good performance and practicality in solving the high-dimensional many-objective flexible job shop scheduling problems, which provides strong support for the intelligent green transformation and the upgrading of manufacturing workshops of enterprises Table and Figures | Reference | Related Articles | Metrics

Select

Research on Learnable Wargame Agent Driven by Battle Scheme Sun Yifeng, Li Zhi, Wu Jiang, Wang Yubin Journal of System Simulation    2024, 36 (7): 1525-1535.   DOI: 10.16182/j.issn1004731x.joss.23-0477 Abstract （4113）   HTML （366）    PDF（pc） （2363KB）（675）       Knowledge map    Save To enable the agent to cope with complex battle scenarios and objectives in wargame, a learnable wargame agent architecture driven by a battle scheme is proposed. By analyzing the "attachment characteristics" and "loose coupling characteristics" of the agent to wargame system, the learnable requirements of the agent are obtained. In the design of the agent framework, battle schemes are used to reduce the learning range of the agent. The finite state machine corresponds to the knowledge of the operational phase in the battle scheme, and the decision-making space of the agent is determined according to the framework of the battle scheme. A learnable deep neural network is designed to explore key decision space. The neural network uses prior knowledge imitation learning mode and deep reinforcement learning mode. This architecture can iteratively explore optimal deployment and collaboration issues for multiple chessmen that are difficult for humans to fully tease out. Table and Figures | Reference | Related Articles | Metrics

Select

Parallax-tolerant Image Stitching with Geometric Structure Protection for Unmanned Ship Visual Perception Yang Zhilin, Yin Yong, Zhang Rukai, Jing Qianfeng, Jiang Sen, Zhu Wenfeng Journal of System Simulation    2024, 36 (8): 1749-1763.   DOI: 10.16182/j.issn1004731x.joss.24-0310 Abstract （4727）   HTML （405）    PDF（pc） （8215KB）（655）       Knowledge map    Save In order to address the artifacts caused by misalignment in maritime image stitch with low texture and large parallax, a geometric structure parallax-tolerant image stitch algorithm based on point-line feature registration and optimal seam fusion is proposed. Line segment features are introduced into the traditional homography transformation based on point features, and potential coplanar local line segments are merged into global line segments to provide accurate alignment conditions for seam line fusion. In the image fusion stage, the energy function of seam cutting method is designed by using the color difference and gradient difference of tanh measure and introducing saliency detection weight, which guides the optimal seam to avoid prominent maritime structures in the image, thus ensuring the continuity of structural edges. The SIFT flow method is used to correct the misalignment pixels on the stitching seam, and the maritime image stitching with accurate geometric structure is realized. Experimental results, based on 20 pairs of diverse scene data, compaed with the baseline method, the proposed algorithm achieves an average 44.6% reduction in seam quality error based on structural similarity, with a maximum reduction of 66.7%. The average reduction in seam quality error based on zero mean normalized cross-correlation is 24.7%, with a maximum reduction of 51.6%. The algorithm can effectively avoid artifacts, thus achieving visually natural stitching results and satisfying the requirements for a wide field of view during unmanned ship navigation. Table and Figures | Reference | Related Articles | Metrics

Select

A Threat Assessment Method in Uncertain Dynamic Environments Yang Mei, Wang Bingkun, Zhang Zhongjie, Zeng Yan, Huang Jian Journal of System Simulation    2024, 36 (12): 2741-2754.   DOI: 10.16182/j.issn1004731x.joss.24-FZ0735 Abstract （1085）   HTML （439）    PDF（pc） （4767KB）（591）       Knowledge map    Save A threat assessment method based on priori information and dynamic observation results is studied for the existence of dynamic uncertainty in complex war systems. The data mining is applied to obtain prior knowledge on the battlefield situation and construct an equipment-related confidence matrix. The sensor model is constructed to dynamically update the number of blue-side entities under the current situation by using the Bayesian method and considering both intelligence and observation results. The threat evaluation indicators and their weights are determined, and the TOPSIS method is used to finish the threat assessment. This method can well describe the complex and changing dynamic battlefield environment and make full use of priori information and dynamic observation results for threat assessment of the detection area or the undetectable location nearby. The feasibility of this method is verified through case simulation analysis. Table and Figures | Reference | Related Articles | Metrics

Select

Traffic Sign Recognition Model with Long-Tail Distribution Based on YOLOX-Tiny Wu Yunpeng, Fu Yingxiong, Shen Lijun, Cui Feng Journal of System Simulation    2024, 36 (11): 2503-2516.   DOI: 10.16182/j.issn1004731x.joss.23-0906 Abstract （863）   HTML （459）    PDF（pc） （5962KB）（586）       Knowledge map    Save Accurate recognition of traffic signs plays an important role in the field of intelligent driving. Traffic sign training datasets with long-tail distribution increase the difficulty of traffic sign recognition. A traffic sign recognition model with long-tail distribution based on YOLOX-Tiny was proposed to improve the poor performance of the model trained on long-tail distribution datasets. A long-tail traffic sign dataset was created based on the TT100K_2021 (tsinghua-tencent 100K 2021) dataset. YOLOX-Tiny was chosen as the underlying model by considering picture numbers in datasets, sample distribution, and model size. Equalization loss v2 (EQL v2) was used as classification loss to balance the head and tail of the classifier, and focal loss(FL) was used as target confidence loss to enhance the model's prediction of target confidence. In order to solvethe backpropagation conflicts of feature graphs at different levels on the traditional feature pyramid, enhance the featurereorganization effect, and highlight target feature, up-sampling operator CARAFE, coordinate attention (CA), and CARAFE + adaptively spatial feature fusion modules (CAR-ASFF) were introduced to the neck bidirectional pyramid. The research results show that the improved YOLOX-Tiny model achieves 43.67% and 29.98% respectively in the long-tail traffic sign datasets, namely mAP50 and mAP50:95. The improved model has higher detection accuracy than other target detection models. Table and Figures | Reference | Related Articles | Metrics

Select

Quadrotor UAV Path Planning Based on Rapidly-exploration Directional Tree Algorithm Hu Shijun, Liu Hailiang, Wang Binglei, Su Wenke Journal of System Simulation    2025, 37 (2): 311-324.   DOI: 10.16182/j.issn1004731x.joss.23-1165 Abstract （467）   HTML （350）    PDF（pc） （3214KB）（582）       Knowledge map    Save Aiming at the problems of low planning success rate, slow convergence speed, and suboptimal paths in the RRT algorithm for quadrotor UAV path planning of in complex environments, a directional exploration tree algorithm is proposed, which uses a directional sampling strategy to improve the directionality of the tree expansion, and by introducing an adaptive target adjustment strategy and a branch expansion strategy, the tree can expand quickly towards the target point while avoiding obstacles. The redundant points in the initial path are removed by the pruning process, and then the trajectory correction and smoothing process are performed on the pruned path to obtain the optimal route. Simulation results show that the proposed algorithm is successful in all tests. relative to the traditional RRT and improved RRT algorithms in multi-obstacle environments, in multi-obstacle environments, in terms of planning time, the proposed algorithm reduces 91.9% and 67%, in terms of path length, the proposed algorithm reduces 37% and 6%; in narrow environments compared in terms of planning time, the proposed algorithm reduces 88.3% and 70%, in terms of path length, the proposed algorithm reduces 36% and 5.6%. Table and Figures | Reference | Related Articles | Metrics

Select

Path Planning of Mobile Robot Based on the Integration of Multi-scale A* and Optimized DWA Algorithm Xu Jianmin, Song Lei, Deng Dongdong, Chen Yaoruo, Yang Wei Journal of System Simulation    2025, 37 (1): 257-270.   DOI: 10.16182/j.issn1004731x.joss.23-1089 Abstract （212）   HTML （9）    PDF（pc） （7005KB）（558）       Knowledge map    Save In order to solve the problems of sharply increasing computational and time costs, as well as poor flexibility of the traditional A* algorithm and dynamic window approach (DWA) in the face of large-scale complex environmental path planning, a fusion algorithm based on the A* algorithm of the multi-scale map approach(MMA) and the improved DWA algorithm is proposed. A multi-scale map set is established and an obstacle proportion factor is added to the heuristic function of the A* algorithm. The A* algorithm is used to calculate the optimal path on the coarse-scale map, and the optimal path is mapped onto the fine-scale map for quadratic A* algorithm planning. The Floyd algorithm is used to optimize the nodes, remove redundant nodes, and improve the smoothness of the path. In addition, the heading angle adaptive adjustment strategy and parking wait state are added to optimize the dynamic window method to improve flexibility. The key points of the A* algorithm are used as local target points of the dynamic window method and replanned when there are obstacles on the path to realize the integration of the two algorithms. The results of ROS simulation and actual vehicle experiments show that the computation time of the improved A* algorithm is significantly reduced by 98% in 20×40 maps and the improved fusion algorithm dramatically improves the smoothing and flexibility of the robot in dynamic environments, and can effectively solve the problems existing in the traditional fusion algorithm Table and Figures | Reference | Related Articles | Metrics

Select

A Multimodal Residual Spatial-temporal Fusion Model Based on Automatic Sleep Classification Guo Yecai, Tong Shuang Journal of System Simulation    2024, 36 (9): 2065-2074.   DOI: 10.16182/j.issn1004731x.joss.23-0588 Abstract （935）   HTML （30）    PDF（pc） （2946KB）（539）       Knowledge map    Save Highly accurate sleep staging plays a crucial role in correctly assessing sleep conditions. Aiming at the problem that the existing convolutional network cannot obtain the topological characteristics of physiological signals, a sleep staging algorithm based on multi-modal residual spatio-temporal fusion is proposed. Time-frequency images and spatio-temporal images are obtained using short-time Fourier transform and adaptive map convolution, which are converted into high-dimensional feature vectors; lightweight interaction of feature information flow is realized through time-frequency feature and spatio-temporal feature extraction modules; the feature enhancement fusion module fuses feature information to outputs sleep staging results. The results show that the model has a high accuracy. On the ISRUC-S3 data set, the overall accuracy is 85.3%, the F1 score is 83.8%, Cohen’s kappa is 81%, and the N1 stage accuracy reaches 69.81%. Experiments on the ISRUC-S1 dataset demonstrate the generality of the model. Table and Figures | Reference | Related Articles | Metrics

Select

Air Defense Missile Weapon Target Assignment Based on Multi-objective Evolutionary Algorithm Sun Xin, Xing Lining, Wang Rui, Wang Ling, Shi Jianmai, Luo Tianyu Journal of System Simulation    2024, 36 (6): 1298-1308.   DOI: 10.16182/j.issn1004731x.joss.24-0118 Abstract （2565）   HTML （129）    PDF（pc） （2037KB）（524）       Knowledge map    Save An effective weapon target assignment method can reduce the combat losses and improve the defense effect. A reasonable mathematical model is established for the allocation of air defense resources, aiming at the optimization objectives of maximizing target destruction effectiveness and minimizing radar resource consumption, considering multiple constraints such as the upper limit of radar channels, on the basis of multiobjective evolutionary algorithm based on decomposition (MOEA/D), the probability of crossover and mutation is adaptively adjusted to improve the quality of individuals in the process of population evolution, and a set of optimal solution sets for decision makers is obtained. The results show that, compared with other multi-objective evolutionary algorithms, the algorithm can obtain the higher fitness values and good distributivity, and can provide a feasible solution to the weapon target assignment for air defense missile. Table and Figures | Reference | Related Articles | Metrics

Select

Adaptive Recognition Method of Capability Boundary Parameters for Unmanned Autonomous Systems Li Jinwen, Wang Peng, Pan Youmei, Hui Xinyao Journal of System Simulation    2024, 36 (10): 2359-2370.   DOI: 10.16182/j.issn1004731x.joss.23-0775 Abstract （267）   HTML （3）    PDF（pc） （2393KB）（502）       Knowledge map    Save To effectively cope with the dimension curse in simulation testing and reduce the number of simulations times needed in the traditional full-space parameter traversal, it is necessary to obtain specific simulation data to accurately reflect the modeling characteristics of the test data to obtain the informative and representative samples of the original data with a smaller number of simulations. A digital simulation test model for adaptive recognition;/of capability boundary parameters for UAS is proposed. The model is initially constructed with a good point set with a multi-weight structure; In combination with an adaptive kernel function boundary point recognition, the model is iteratively optimized by Gaussian process regression, so as to adaptively detect the capability boundary of UAS. The experimental results show that the method can reduce the amount of data required for modeling and improve the efficiency of adaptive parameter boundary recognition, which provides an approach to enhance the efficiency of intelligent UAS testing. Table and Figures | Reference | Related Articles | Metrics

Select

Research on Virtual Simulation Testing Technology for Intelligent Navigation Collision Avoidance Decision-making and Planning Liu Jialun, Yang Fan, Xie Lingli, Li Shijie, Wang Tengfei Journal of System Simulation    2024, 36 (8): 1780-1789.   DOI: 10.16182/j.issn1004731x.joss.24-0412 Abstract （4929）   HTML （250）    PDF（pc） （3352KB）（466）       Knowledge map    Save This paper studies virtual simulation testing technology for intelligent navigation collision avoidance decision-making and planning. The application requirements of intelligent navigation in cargo ships are introduced, and the current research status of collision avoidance decision-making strategies, path planning algorithms and decision-making planning testing technology are analyzed. For the intelligent navigation collision avoidance decision-making and planning capabilities of cargo ships, an intelligent navigation collision avoidance decision-making and planning algorithm is proposed based on the encounter situation division in the collision avoidance rules, combined with the quaternary ship field and Bezier curve interpolation theory. A simulation testing method for decision-making planning algorithms based on virtual simulation environment was constructed. The AIS (automatic identification system) simulator is used to simulate the status data of the target ship, and combined with the shipboard INS (integrated navigation system), the decision-making planning algorithm is tested. The effectiveness and feasibility of the proposed algorithm are verified through complex water simulation tests, which provides an important reference for the development and practice of intelligent navigation functions for cargo ships. Table and Figures | Reference | Related Articles | Metrics

Select

Reserach on Digital Twins Technology in Cyberspace Security Ren Qiankun, Xiong Xinli, Liu Jingju, Yao Qian Journal of System Simulation    2024, 36 (8): 1944-1957.   DOI: 10.16182/j.issn1004731x.joss.23-0853 Abstract （404）   HTML （11）    PDF（pc） （2984KB）（462）       Knowledge map    Save Combined with digital twins and cyber-space modeling and simulation, the network digital twins (NDT) technology with in-deep research can enable the development of diverse techniques of cyber security. The basic concept and research history of NDT are summarized, and a taxonomy is proposed to survey applications of NDT. A cyber security-oriented network digital twin model (CyS-NDT) is concluded through the literature. The relationship between the internal security problem of NDT and the method of enabling network security technology is discussed to prospect further challenges and opportunities. Table and Figures | Reference | Related Articles | Metrics

Select

Task Reallocation Method for Unmanned Swarm Under Adversarial Conditions Zhang Lun, Yang Mei, Zhao Tuo, Zhang Shuiku, Huang Jian Journal of System Simulation    2025, 37 (1): 1-12.   DOI: 10.16182/j.issn1004731x.joss.24-1005 Abstract （517）   HTML （229）    PDF（pc） （2689KB）（446）       Knowledge map    Save Heterogeneous unmanned swarms have important potential applications in future wars. However, during the high-intensity confrontation in the battlefield, how to efficiently and quickly redistribute the tasks carried by the damaged agents so that the swarms could successfully complete the mission is a difficult problem that must be addressed in the combat application of unmanned swarms. This paper proposes a task reallocation method named improved CNP-HA (contract net protocol-Hungarian algorithm). Through the allocation mechanism and the bidding mechanism, the method realizes the task reallocation of damaged agents with lower communication cost and faster speed comparing with baseline methods. In the simulation experiment, when a single agent is damaged, the average completion rate of target reallocation is increased from 87% to 100% by the proposed method, and the target reallocation can still be completed stably when multiple agents are damaged, and the resource scheduling rate and rapidity of the proposed method are better than the comparison algorithms. Table and Figures | Reference | Related Articles | Metrics

Select

Digital Twin Method of Stress Field of Deep Submersible Spherical Shell Based on Simulation Database Cao Yu, Li Jie, Wang Fang, Liu Zhixiang, Wang Xueliang Journal of System Simulation    2024, 36 (8): 1764-1779.   DOI: 10.16182/j.issn1004731x.joss.24-0173 Abstract （5257）   HTML （289）    PDF（pc） （7863KB）（443）       Knowledge map    Save This paper presents a method for predicting the stress field of deep diving spherical shells based on simulation databases and digital twin technology. By establishing simulation databases of stress field distribution of pressure-resistant spherical shells under different scales and loads, virtual sensing monitoring of stress states in other parts of the vessel is realized through finite sensor layout of pressure-resistant shells on the submersible. Based on the DT(digital twin) technology, a three-level virtual structure layer is constructed. The Level-1 DT layer realizes the spatial mapping and cloud image display from the finite element simulation model to the digital model. The error between the experimental and numerical results of the ultimate bearing capacity of the spherical shell is less than 9.4%. The Level-2 DT layer realizes the data sample deduction of the digital model by create database. The stress field distribution of the spherical shell under the condition that the size and load are not obtained in the simulation database is obtained by the local Lagrange interpolation method. The relative error of the stress interpolation result is 4.8%. The Level-3 DT layer develops a machine learning prediction function for the stress field distribution in the dangerous area of the deep-submersible spherical shell digital model. The BP neural network optimized by the particle swarm optimization algorithm ensures that the error between the prediction result and the simulation result is less than 1%. This method comprehensively considers the material properties, structural dimensions and environmental loads, which can provide a reference for the real-time safety assessment of the pressure hull structure, and realize the dynamic perception, intelligent diagnosis and scientific prediction of the dynamic stress field distribution of all deep-submersible spherical shells on the hull. Table and Figures | Reference | Related Articles | Metrics

Select

Construction of a Virtual Interactive System for Orchards Based on Digital Twin Wang Hongjun, Lin Junqiang, Zou Xiangjun, Zhang Po, Zhou Mingxuan, Zou Weirui, Tang Yunchao, Luo Lufeng Journal of System Simulation    2024, 36 (6): 1493-1508.   DOI: 10.16182/j.issn1004731x.joss.23-0317 Abstract （519）   HTML （22）    PDF（pc） （12318KB）（425）       Knowledge map    Save Aiming at the low visibility, poor real-time, weak adaptability and single interaction mode in orchard planting management system, a six-dimensional model of orchard digital twin system for planting management process is proposed. The system model construction theory and technology system is discussed from four aspects, entity modeling of management elements, dynamic modeling of management process, simulation modeling of management system and optimization modeling of management strategy. Based on the six-dimensional model, supported by the theory and technology system, the virtual interactive system architecture of the orchard based on the digital twin is designed, and the key technologies of the system development process are standard. With the Unity3D simulation platform, the orchard virtual interactive system is built to realize the three-dimensional visualization monitoring of the orchard. The experimental results show that the system improves the monitoring ability of orchard plantation management system through data-driven, 3D display, human-computer interaction, reconstructed events and intelligent decision-making on the basis of data sharing on the platform of internet of things in agriculture, which provides a reference for the construction of smart orchard. Table and Figures | Reference | Related Articles | Metrics

Select

Digital Application of Equipment System Test and Evaluation Based on Digital Twin and Parallel Experiment Theory Dang Hongjie, Yu Wenguang, Yang Huahui Journal of System Simulation    2024, 36 (7): 1729-1736.   DOI: 10.16182/j.issn1004731x.joss.23-0433 Abstract （410）   HTML （19）    PDF（pc） （2825KB）（421）       Knowledge map    Save With the development of equipment systematization,traditional test with real equipment can not meet the requirements of Test and Evaluation(T&E), especially for complex equipment. As the main digital methods in current, digital twins and parallel experiments can support the digital application in the field of equipment Test and Evaluation. This paper makes a comparative analysis of the two digital technology means, extracts their technical connotation and characteristics, and then integrates them to explore the application mode, application time and application occasions in the field of equipment T&E. Taking the satellite for example, by constructing the digital architecture of equipment systemT&E based on digital twin and parallel tests, the feasible digital application scheme is designed. The confidence and reliability of the digital model in the equipment system test and evaluation model library are verified through two typical test scenarios. Furthermore, it provides data support for the future on-orbit mission embodiment design and performance evaluation and provides an overall idea for the development of equipment system T&E. Table and Figures | Reference | Related Articles | Metrics

Select

Optimal Scheduling of Vehicle-network Interaction Based on Interval Stackelberg Game of Virtual Power Plant Liu Weiliang, Yan Qianwen, Zhang Qiliang, Liu Shuai, Liu Changliang, Kang Jiayao, Wang Xin Journal of System Simulation    2024, 36 (7): 1559-1572.   DOI: 10.16182/j.issn1004731x.joss.23-0503 Abstract （4452）   HTML （222）    PDF（pc） （5462KB）（418）       Knowledge map    Save To better exploit the regulation potential of electric vehicles (EVs), resolve the conflicts of interest among the stakeholders in vehicle-to-grid (V2G) interactions, and overcome the uncertainty of distributed energy sources and load, this paper proposes a two-level optimization scheduling model for V2G interactions based on the interval Stackelberg game of a virtual power plant (VPP). The VPP aggregator is considered as the upper level, and the EV users as the lower level. The upper level model uses interval numbers to describe the uncertainty of sources and loads, with the aim of minimizing the operating cost of the VPP aggregator, updating the electricity price information and transmitting it to the lower level model. The lower level model aims to maximize user satisfaction and minimize costs by solving the charging and discharging behavior of EV users and returning the results to the upper level model. The improved particle swarm optimization algorithm with integrated interval possibility degree is used to obtain the optimal scheduling results of the Stackelberg game. Simulation results demonstrate that the proposed model can effectively shave peak and fill the valley, coordinate the bilateral interests of the aggregator and EV users, and has good robustness. Table and Figures | Reference | Related Articles | Metrics

Select

Research on Operational Protection Area of ILS Glide Slope Li Qingdong, Ye Jiaquan, Xu Jian Journal of System Simulation    2024, 36 (6): 1273-1284.   DOI: 10.16182/j.issn1004731x.joss.23-0133 Abstract （2158）   HTML （178）    PDF（pc） （3995KB）（414）       Knowledge map    Save The scientific protection for the operational protection area of the instrument landing system glide slope is of great significance to ensure the quality of civil aviation navigation space signals, the safety of aircraft approach operations, and the efficiency of airport operations. Combined with the concept evolution of the glide slope operational protection area, a comparative analysis of the delineation of the glide slope operational protection area required by the national civil aviation standards, industry standards, and Annex 10 Volume I of the Convention on International Civil Aviation is carried out. Taking the extra-large aircraft (A380-800) as an example, the glide slope operational protection area of a specific operation category is studied in the form of computer simulation, which maybe a supplement to relevant data on glide slope protection areas in Annex 10 Volume I of the Convention on International Civil Aviation and an example of the actual engineering demonstration. The typical research methods of glide slope site protection for the actual operation of specific airports and protection suggestions for glide slope operational protection area are given as the references for airport construction and operation. Table and Figures | Reference | Related Articles | Metrics

Select

UAV Dynamic Path Planning Algorithm Combined with Dynamic Window Approach Liu Bin, Lan Ying, Huang Wentao, Fan Qinqin Journal of System Simulation    2024, 36 (8): 1843-1853.   DOI: 10.16182/j.issn1004731x.joss.23-0993 Abstract （432）   HTML （9）    PDF（pc） （1865KB）（408）       Knowledge map    Save To solve the problem of the poor search for optimal performance and obstacle avoidance ability of path planning algorithms in complex dynamic environments, a UAV dynamic path planning algorithm combined with dynamic window approach (UAV-DPPA-DWA) is proposed. In the UAV-DPPA-DWA algorithm, a novel elliptic tangent graph algorithm based on the evaluation of offset degree and obstacle distance is proposed to obtain the optimal guidance path for the UAV in static environments. If the UAV detects moving obstacles, a localized obstacle avoidance trajectory will be generated using the dynamic window method with adaptive parameters. Otherwise, the UAV will continue to fly along the guidance path obtained in the static environment. Various types of complex dynamic obstacle avoidance scenarios are presented to verify the performance of the proposed algorithm in terms of both path length and flight time. The experimental results show that, compared with the DWA, A*-DWA, RRT-DWA and PRM-DWA algorithms, the UAV-DPPA-DWA not only has a stronger obstacle avoidance capability to achieve a feasible flight trajectory, but also can complete the task along the optimal path in shorter time. Table and Figures | Reference | Related Articles | Metrics

Select

Hybrid Flow Shop Scheduling with Limited Buffers Considering Energy Consumption and Transportation Wen Tingxin, Guan Tingyu Journal of System Simulation    2024, 36 (6): 1344-1358.   DOI: 10.16182/j.issn1004731x.joss.23-0343 Abstract （1454）   HTML （42）    PDF（pc） （3449KB）（406）       Knowledge map    Save Aiming at the untimely production scheduling and excessive energy consumption during processing, a limited buffer hybrid flow shop scheduling optimization model is constructed. To minimize the makespan and total energy consumption of the workshop, the transport time, generalized energy consumption and buffer capacity being the constraints, and the on/off energy saving strategy applied to reduce the standby energy consumption, the feasibility of the optimization model are verified. A lion swarm optimization algorithm is designed, in which a population initialization method combining random generation and greedy selection is used to improve the initial solution quality and solution efficiency, the lion swarm optimization algorithm superiority is verified. The experimental results show that the algorithm can effectively solve the hybrid flow shop scheduling problem with limited buffer considering energy consumption and transportation time, and the established optimization model can be flexibly adjusted according to the actual needs, in which the purpose of rational production scheduling, energy saving and emission reduction for manufacturing enterprises can be achieved. Table and Figures | Reference | Related Articles | Metrics

Select

An Intelligent Adversaries Behavior Simulation Technology Based on Improved Behavior Trees Zhou Fang, Fan Bo, Liu Xiaoyi, DingYishan , Zhang Ningxin, Shao Yachao, Zhai Xiaoyu Journal of System Simulation    2024, 36 (9): 1995-2003.   DOI: 10.16182/j.issn1004731x.joss.24-0364 Abstract （2393）   HTML （181）    PDF（pc） （3175KB）（405）       Knowledge map    Save Intelligent algorithm/intelligent platform/intelligent system intelligence capability testing and evaluation need to solve high-level intelligent opponent simulation problems, an intelligent opponent behavior simulation technology based on improved behavior tree is proposed. Four types of behavior tress nodes are designed, including behavior control, combat tasks, behavior actions, and execution condition node. Five atomic behavior actions and parameters are established, including maneuver, reconnaissance and early warning, command and decision-making, firepower strike, and electronic interference node. Five atomic condition nodes are provided, including target selection, weapon launch,and incoming weapon judgment node. The intelligent adversarial behavior simulation system is designed, including a behavior rule editor and a behavior rule engine. The adversaries behavior simulation execution process is established. Considering the typical application scenarios of air ground collaborative confrontation in border areas, the simulation results indicate that the simulated intelligent opponent behavior can support the evaluation of intelligent capabilities. Table and Figures | Reference | Related Articles | Metrics

Select

Dynamic Air Defense Resource Allocation Optimization Based on Improved Differential Evolution Algorithm Luo Tianyu, Xing Lining, Wang Rui, Wang Ling, Shi Jianmai, Sun Xin Journal of System Simulation    2024, 36 (6): 1285-1297.   DOI: 10.16182/j.issn1004731x.joss.24-0116 Abstract （2258）   HTML （156）    PDF（pc） （1238KB）（390）       Knowledge map    Save Based on the integrated performance of weapon equipments such as radars, launchers and missiles, a mixed-integer decision model that minimizes the total target intercept value and the probability of survival based on Target-Set, Resource-Set is developed. A new improved differential evolutionary algorithm has been introduced to solve the problem, and the initial solutions is generated by using the reverse learning strategies to ensure the quality of the initial populations. An inspiration rule for the fast repair and reconstruction is designed to work at multi-stage to improve the search capability of the algorithm. The simulation experiment results show the algorithm's superiority in search time and search accuracy, which can maintain the efficient combat capabilities and decision-making under the random influence of dynamic events. Table and Figures | Reference | Related Articles | Metrics

Select

An Empirical Analysis of New Perspectives for Strategy Solving in Intelligent Game-theoretic Decision-making Su Jiongming, Luo Junren, Chen Shaofei Journal of System Simulation    2025, 37 (2): 345-361.   DOI: 10.16182/j.issn1004731x.joss.23-1180 Abstract （289）   HTML （33）    PDF（pc） （4727KB）（380）       Knowledge map    Save With the development of artificial intelligence technology, especially the promotion of large-scale pre-training model theory, some new perspectives of strategy solving for intelligent game-theoretic decision-making have gradually been widely concerned and discussed. This paper combines the development of artificial intelligence technology and the transformation of strategy solving paradigm for intelligent game-theoretic decision-making, takes Chess (two-player zero-sum perfect information game), diplomacy (multi-player general-sum imperfect information game), and StarCraft Multi-Agent Challenge (multi-agent Markov game) as the research object for empirical analysis on sequential decision-making, the new paradigm and new way of strategy solving are analyzed according to the new perspective of artificial intelligence development. The key technologies of the intelligent game decision-making model are analyzed from three aspects: the decision grand model paradigm, the generative artificial intelligence model, the large model agent, which provides reference for the research of intelligent game theoretic decision-making under the new technology system. Table and Figures | Reference | Related Articles | Metrics

Select

Garage AGV Path Planning and Simulation Based on Improved DWA Ma Zongfang, Zhang Linxuan, Song Lin, Wang Jia Journal of System Simulation    2024, 36 (10): 2265-2276.   DOI: 10.16182/j.issn1004731x.joss.23-0638 Abstract （1351）   HTML （87）    PDF（pc） （4224KB）（373）       Knowledge map    Save Aiming at the path planning and real-time obstacle avoidance of AGV in complex path environment of intelligent garage, an improved hybrid algorithm combining ant colony algorithm and dynamic window method is proposed. In the global planning, the adaptive adjustment of pheromone volatilization coefficient and the fusion of angle parameters are introduced to establish the garage direction pheromone matrix to increase the guidance ability of target points, expand the direction selectivity of ants. In the local planning, the improved DWA of the obstacle distance evaluation sub-function based on elliptic equation is designed. By extracting the global path node of the improved ant colony algorithm as the new path evaluation sub-function, and under the global path constrains, the optimality of dynamic planning is realized. The system simulation results show that the algorithm can reasonably cars deal with the dynamic and static obstacles, more in line with the requirements of dynamic programming under the influence of multiple environmental factors in the actual operation of AGV. Table and Figures | Reference | Related Articles | Metrics

Select

Real-time Non-photorealistic Rendering Method for Black and White Comic Style in Games and Animation Hu Yan, Chen Lizhe, Xie Hanna, Ge Yuyao, Zhou Shun, Cai Xingquan Journal of System Simulation    2024, 36 (7): 1699-1712.   DOI: 10.16182/j.issn1004731x.joss.23-0458 Abstract （322）   HTML （7）    PDF（pc） （4559KB）（370）       Knowledge map    Save To address the issues of high resource consumption and lengthy workflow in general non-photorealistic, this paper proposes a real-time non-photorealistic rendering method for black and white comic style in games and animation. A specialized lighting model is designed to highlight the main environmental light and the grayscale grading of diffuse reflection based on the analysis of the lighting model effect. The pre-processing of the scene is achieved by merging the various components of the lighting model. A screen space three-phase edge detection method is proposed to sequentially perform depth edge detection, normal edge detection, and color edge detection on the pre-processed scene lighting results, and the edge detection results are combined. The scene lighting results are rendered by screen space partitioning, utilizing dot shading and line shading respectively based on the grayscale value of the lighting results, with interpolation applied to shading boundaries. The results are merged by designing a segmented function based on the grayscale value of the lighting model results, combining the screen space three-phase edge detection results with the screen space partition rendering results to obtain the final rendered output. Experimental results demonstrate that the proposed method can achieve non-photorealistic rendering of black and white comic style with relatively low resource consumption and reduced error rate, showcasing a distinctive black and white comic style. Table and Figures | Reference | Related Articles | Metrics

Select

Classification Cooperative Scheduling of U-automated Container Terminal Based on Container Markers Wang Fei, Chang Daofang, Wen Furong Journal of System Simulation    2024, 36 (6): 1392-1403.   DOI: 10.16182/j.issn1004731x.joss.23-0333 Abstract （296）   HTML （3）    PDF（pc） （1711KB）（365）       Knowledge map    Save To improve the confusing scheduling of U-shaped yard operations due to improper classification of containers, the classification cooperative scheduling process is proposed, in which the classification cooperative scheduling model is established with the constraints of coordinated operation and efficient independent operation. The container classification principle and the container multiple stacking principle are proposed, the stacking point is selected by the weighted calculation based on the container operation mark to design the penalty mechanism, and the classification cooperative heuristic algorithm solution model is designed.Comparative experiments show that the strategy used in the algorithm is superior,which can reduce the equipment waiting time for each other in the operation. As the size of the experiment increases, the proportion of waiting time decreases and the overall operational efficiency of the U-shaped yard increases. Table and Figures | Reference | Related Articles | Metrics

Select

Object Detection of Lightweight Transformer Based on Knowledge Distillation Wang Gaihua, Li Kehong, Long Qian, Yao Jingxuan, Zhu Bolun, Zhou Zhengshu, Pan Xuran Journal of System Simulation    2024, 36 (11): 2517-2527.   DOI: 10.16182/j.issn1004731x.joss.24-0754 Abstract （796）   HTML （67）    PDF（pc） （4776KB）（365）       Knowledge map    Save In autonomous driving, the efficiency and accuracy of object detection are significant. Object detection based on Transformer structure has gradually become the mainstream method, eliminating the complex anchor generation and non-maximum suppression (NMS). It has problems of high computing cost and slow convergence. An object detection model of the based lightweight pooling transformer (LPT) is designed, which contains a pooling backbone network and dual pooling attention mechanism. A general knowledge distillation method is intended for the DETR (detection transformer) model, which transfers prediction results, query vector, and features extracted by the teacher as knowledge to the LPT model to improve its accuracy. To verify the application potential of the distilled LPT model in autonomous driving, extensive experiments are conducted on the MS COCO 2017 dataset. The results show that the method has great efficiency and accuracy, and is competitive with some advanced techniques. Table and Figures | Reference | Related Articles | Metrics

Select

Curriculum Learning-based Simulation of UAV Air Combat Under Sparse Rewards Zhu Jingyu, Zhang Hongli, Kuang Minchi, Shi Heng, Zhu Jihong, Qiao zhi, Zhou Wenqing Journal of System Simulation    2024, 36 (6): 1452-1467.   DOI: 10.16182/j.issn1004731x.joss.23-0349 Abstract （342）   HTML （8）    PDF（pc） （4714KB）（364）       Knowledge map    Save To address the limited exploration capabilities and sparse rewards of conventional reinforcement learning methods in air combat environment, a curriculum learning distributed proximal policy optimization (CLDPPO) reinforcement learning algorithm is proposed. A reward function informed by professional empirical knowledge is integrated, a discrete action space is developed, and a global observation and local value and decision network featuring separated global and local observations is established. A methodology for unmanned aerial vehicles UAVs is presented to acquire combat expertise through a sequence of fundamental courses that progressively intensify in their offensive, defensive, and comprehensive content. The experimental results show that the methodology surpasses the specialist system and the other mainstream reinforcement learning algorithms, which has the ability of the autonomous acquisition of air warfare tactics and can enhance the sparse rewards. Table and Figures | Reference | Related Articles | Metrics

Select

Simulation of Robotic Peg-in-hole Assembly Strategy Based on DRL Zhu Zilu, Liu Yongkui, Zhang Lin, Wang Lihui, Lin Tingyu Journal of System Simulation    2024, 36 (6): 1414-1424.   DOI: 10.16182/j.issn1004731x.joss.23-0518 Abstract （473）   HTML （22）    PDF（pc） （2440KB）（361）       Knowledge map    Save Aiming at the existing peg-in-hole assembly method problems of dependence on accurate contact state models, difficulties in data acquisition, low sampling efficiency, and poor security, a simulation research method for robot peg-in-hole assembly strategy based on DRL is proposed. A simulation environment of robot peg-in-hole assembly based on ROS-Gazebo is built, and a method of gravity compensation for force/torque sensor based on a least square method is proposed. The reinforcement learning paradigm is employed to model the robot peg-in-hole assembly, and a method based on soft actor-critic(SAC) algorithm is proposed. The communication mechanism between the simulation environment and the deep reinforcement learning algorithm is established through ROS. Simulation experiments show that the proposed SAC algorithm enables robots to accomplish the peg-in-hole assembly task autonomously and compliantly with good generalization ability. Table and Figures | Reference | Related Articles | Metrics

Select

Effective Position Intelligent Decision Method Based on Model Fusion and Generative Network Guo Liqiang, Ma Liang, Zhang Hui, Yang Jing, Li Lianfeng, Zhai Yaqi Journal of System Simulation    2024, 36 (7): 1573-1585.   DOI: 10.16182/j.issn1004731x.joss.22-1265 Abstract （4228）   HTML （181）    PDF（pc） （4616KB）（361）       Knowledge map    Save Military intelligence technology is currently the most dynamic frontier and the inevitable trend for the development of unmanned equipment in the future. Aiming at the dual requirements of reliability and real-time performance of unmanned platform autonomous decision-making in complex environments and the shortcomings of existing combat simulation technology based on rule reasoning in terms of dynamics and flexibility, a research method of principle analysis and experimental verification is adopted. Based on the shooting experiment dataset of an unmanned platform, the effective position recognition link of attack decision-making is transformed into a binary classification problem with imbalanced categories in the field of machine learning. The effective position intelligent decision-making model with high real-time performance and flexibility is constructed by using correlation analysis, feature engineering, and model fusion technology. Based on the imbalanced classification architecture of ICGAN-Stacking, directional expansion of minority class samples is proposed to achieve data enhancement and model performance improvement. The experimental results show that the recall rate of the proposed method has increased by 4.1%, the accuracy by 0.4%, and the F1 value by 1.5%, and the AUC value reaches 90.9%, which can meet the real-time performance and reliability requirements of the unmanned platform in performing combat tasks. Table and Figures | Reference | Related Articles | Metrics

Select

Arterial Coordination Optimization Method Based on Vehicle Speed Guidance and Inductive Control Deng Mingjun, Hu Xinxia, Li Xiang, Xu Liping Journal of System Simulation    2024, 36 (6): 1309-1321.   DOI: 10.16182/j.issn1004731x.joss.23-0315 Abstract （2401）   HTML （123）    PDF（pc） （2780KB）（359）       Knowledge map    Save Arterial signal coordination is usually based on fixed belt speeds and time-of-day statistical flows. Actually, vehicle speeds and traffic flows are fluctuating, which causes to the mismatch between the signal scheme and the actual optimal belt speeds and traffic flow demands, and affects the intersection's traffic efficiency. Based on the vehicle infrastructure cooperation, by applying Maxband model and the maximum green wave bandwidth, the minimum number of arterial vehicle delays, arterial stops and the minor direction delays being the optimization objectives, a multi-objective optimization model for arterial signal coordination is established. Through using an improved multi-objective particle swarm algorithm the model is solved to obtain the parameters of the coordinated intersection global control scheme. A vehicle speed guidance model is proposed based on the intersection inlet lane vehicle location and signal state. According to the vehicle saturation of the inlet lane of the arterial intersection, an inductive control strategy is applied to adjust the green light timing of each intersection in real time on the basis of global coordination. The results show that the optimization model combines the speed guidance and signal coordination, considers the mainline intersection loading degree situation, dynamically adjusts the green time, reduces the number of delays and stops at intersections, and can effectively improve the efficiency of arterial coordination control. Table and Figures | Reference | Related Articles | Metrics