Table of Content

30 November 2022, Volume 43 Issue S2

Previous Issue    Next Issue

Electronic edition of this issue

Electronic edition of this issue

2022, 43(S2):  0. 

Asbtract ( )   PDF (71934KB) ( )  

Related Articles | Metrics

Contents

Contents

2022, 43(S2):  0. 

Asbtract ( )   PDF (900KB) ( )  

Related Articles | Metrics

Paper

Development Tendency of Terminal Anti-missile Small-caliber Gatling Gun Technology

QIU Zhiming, CAO Yuan

2022, 43(S2):  1-6.  doi:10.12382/bgxb.2022.B025

Asbtract ( )   PDF (2621KB) ( )  

References | Related Articles | Metrics

The terminal anti-missile small-caliber Gatling gun has the characteristics of high emissivity, good reliability and strong combat capability, which is an important link in the anti-missile combat system. This paper summarizes the development history and technical characteristics of the small-caliber Gatling gun at home and abroad such as Phalanx, Kortik and Goalkeeper, and analyzes various challenges including hypersonic speed, orbit transfer and saturation attack with groups of missiles in the terminal anti-missile operations. The development requirements for faster speed, higher accuracy, stronger damage and enhanced capability of sustained combat is systematically summarized. The development tendency of the terminal anti-missile small-caliber Gatling gun is discussed from four aspects, including the technology of the small-caliber Gatling gun with extreme rate of fire, the integration technology of ammunition feeding-reloading and ammunition storage, the integrated defense technology of terminal multiple weapons and the technology of small-caliber Gatling gun plus intelligence.

Integrated Design Method for Warship Platform Maneuver Route and Missile Attack Path

YANG Huadong, ZHOU Mo, SUN Haiwen

2022, 43(S2):  7-12.  doi:10.12382/bgxb.2022.B020

Asbtract ( )   PDF (1075KB) ( )  

References | Related Articles | Metrics

To deal with the conflict between the action planning of the ship platform and the fire maneuver planning, which leads to the problems of recalculation and low efficiency of force and fire action planning, an integrated design method for ship platform maneuver route and missile attack path is proposed. Firstly, according to the platform motion parameters of both sides and the terminal attack angle or attack direction of the missile, based on the shortest-time maneuver tactics of the platform, the virtual warship-target encounter point prediction and the dynamic planning of the missile flight path are performed. Secondly, the maneuvering course, maneuvering time and range of the ship platform are calculated iteratively, and the missile launch point of the platform is recommended. Finally, the realization steps of the shortest-time contact maneuver of the ship platform under the missile's direct navigation mode and route planning mode are given respectively. With the proposed method, after the ship platform reaches the recommended launch point, it can immediately launch missiles according to the planned missile flight route, make full use of the missile range, and launch at the farthest possible distance to achieve the effect of launching and hitting before the enemy.

A Target Identification Technique for Unmanned Surface Vessel Based on Deep Learning

WANG Liang, CHEN Jianhua, LI Ye

2022, 43(S2):  13-19.  doi:10.12382/bgxb.2022.B021

Asbtract ( )   PDF (4749KB) ( )  

References | Related Articles | Metrics

At present, China is vigorously developing marine weapons and equipment, and the research on unmanned weapons and equipment has received extensive attention. The intelligentization of unmanned surface vessels is a research hotspot. To meet the detection and high-precision positioning requirements of large and medium-sized targets, this paper focuses on the design of target identification technique for unmanned surface vessel based on deep learning. Firstly, the multi-source and multi-system collaborative sensing architecture design is used to solve the problems of equipment intelligent computing task duplication and resource waste as well as deep learning acceleration. Secondly, multi-level feature extraction, analysis and fusion technique is designed to determine the features that should be selected for single/multi-sensors. Finally, the selected features are used to design multi-feature target detection and identification methods based on deep learning, and a multi-source multi-dimensional joint detection and identification processing method based on deep learning networks is established. The experimental results show that the recognition rate exceeds 99.7% for visual images, indicating that this technique has good recognition effects.

USV Trajectory Tracking Control Algorithm of Based on the Line-of-sight Guidance Strategy

WANG Lian, LI Ye, CHEN Xiao, LUO Rong, WANYAN Juan, TANG Jiayu

2022, 43(S2):  20-25.  doi:10.12382/bgxb.2022.B008

Asbtract ( )   PDF (1881KB) ( )  

References | Related Articles | Metrics

To realize the precise tracking and safe navigation control of the unmanned surface vehicle (USV) in the complex ocean environment, firstly, the line-of-sight (LOS) guidance strategy used in USV trajectory tracking control is studied in detail, and the algorithms are divided into two categories: LOS guidance strategy based on look-ahead distance and on encircling circle. Then, the mathematical model of the USV is built, and the USV trajectory tracking control algorithm is designed based on the LOS guidance strategy using the look-ahead distance and the PID control idea. Finally, the simulation results show that the proposed algorithm has good trajectory tracking control effects, which can provide insights into research on the autonomous navigation control technology and the construction of the USV equipment in China.

Influence of Warhead Parameters of Munitions Against USV Group on Combat Effectiveness

FENG Wei, CUI Donghua, LIU Haixiao, ZHOU Mo, LI Heng, HU Zhipeng

2022, 43(S2):  26-31.  doi:10.12382/bgxb.2022.B004

Asbtract ( )   PDF (1865KB) ( )  

References | Related Articles | Metrics

In recent years, with the rapid development of autonomous perception, autonomous collaboration, and autonomous control technologies, the USV group has gradually gained operational capabilities. However, there are no efficient counter-USV group munitions and equipment yet. To deal with the difficulty in countering the USV group, based on the terminal-sensitive detection technology, we propose a gun-launched munition that uses the MEFP warhead for damage. The Monte Carlo simulation of target practice is adopted to simulate the utilization of the munition in operations, and the design of the warhead's scattering angle considering a variety of factors is analyzed. The effects of the gun-target distance, the number of targets, the movement speed, and the target size on the damage effectiveness of the munition are investigated. The simulation results show that the terminal-sensitive gun-launched munition is effective in anti-USV group operations. The proposed solution can provide reference and inspiration for China's development of anti-USV group munitions and equipment.

Target Threat Assessment Method for UAV Swarm at Sea

SUN Haiwen， YU Shaozhen， JIANG Yuan, ZHOU Mo， TANG Jiayu， LI Dan

2022, 43(S2):  32-39.  doi:10.12382/bgxb.2022.B006

Asbtract ( )   PDF (1263KB) ( )  

References | Related Articles | Metrics

To solve the problem of target threat assessment of UAV swarm at sea, we build a UAV swarm threat assessment index system, construct a UAV swarm threat assessment model, propose an improved UAV swarm threat ranking method based on TOPSIS (ITOPSIS) and design a secondary threat assessment process. Simulation analysis shows that this method can effectively and accurately assess the threat of multi-batch UAV swarm targets, which can provide reference for making combat command decisions to fight against UAV swarm.

Path Planning for Coverage Search for Submarines Using Fixed-wing UAVs in Complex Irregular Sea Area

MA Yan, FENG Wei, LUO Rong, LI Ye, MENG Xiangyao

2022, 43(S2):  40-52.  doi:10.12382/bgxb.2022.B024

Asbtract ( )   PDF (8675KB) ( )  

References | Related Articles | Metrics

To deal with the problem of using fixed-wing unmanned aerial vehicles (UAVs) for fast coverage search for submarines in large sea area, a Dubins path search strategy for the selective removal of concave points in regions in complex, irregular polygonal shapes was proposed. Firstly, a mathematical model of UAV searching and detection cost was established. Combined with the turning characteristics of fixed-wing UAVs, the Dubins path method was introduced based on the traditional method of UAV's coverage search in convex polygonal regions.Then, in order to avoid “violent” removal of all concave points for the irregular concave polygonal regions, an improved concave point removal method was proposed, which turned the irregular concave polygon region into a regular convex polygonal region. Finally, a comparison and verification experiment of the UAV coverage search strategy in regions with complex boundaries was designed. The simulation results showed that the method of removing the concave points on the boundary of the polygonal region and searching according to the Dubins path in the search direction along the span can greatly reduce the invalid navigation cost of the detection and coverage search, which can provide theoretical support for efficient submarine search.

Numerical Simulation of Flow Characteristics of the Underwater Vehicle with a Cylindrical Structure Based onDifferent Turbulence Models

HE Jiawei, ZHAI Junyi, GAO Weipeng, LI Ye

2022, 43(S2):  53-63.  doi:10.12382/bgxb.2022.B022

Asbtract ( )   PDF (14143KB) ( )  

References | Related Articles | Metrics

In order to improve the stealth performance of underwater vehicles, the effects of different turbulence models on the numerical simulation of the underwater vehicle with a cylindrical structure are investigated. Numerical simulations have been carried out by using the open source computational fluid dynamics toolbox called OpenFOAM. Three hybrid turbulence models were developed and embedded in the OpenFOAM toolbox. The three models are the Scale Adaptive Simulation (SAS) method, the Partially Averaged Navier-Storks (PANS) equation method and the Improved Delayed Detach Eddy Simulation (IDDES) method. Based on the developed three models, numerical computations were performed to obtain the distribution of the flow field and force characteristics. The results showed that the turbulence model selection has a significant influence on the hydrodynamic simulation of the underwater vehicle, which may provide guidance for the subsequent research on the stealth technology of underwater vehicles.

Foreign Unmanned Equipment and Technology Development in Mine Countermeasures

XU Tongle, LIU Fang, XIAO Yujie， WANG Shen, BAI Yihui, LUO Rong

2022, 43(S2):  64-70.  doi:10.12382/bgxb.2022.B019

Asbtract ( )   PDF (4438KB) ( )  

References | Related Articles | Metrics

As natioans are pursing the concept of “zero casualties”, the unmanned minefield has gradually become the trend of future mine warfare. As a new type of combat force, the development of unmanned systems in the anti-mine field has attracted much attention, which is worthy of further study. Based on the current situation of unmanned mine countermeasure development abroad, the technical characteristics and typical equipment indicators of UUVs, UAV,s and USVs are compared. The key techniques in unmanned mine countermeasure equipment in the fields of energy power, autonomous control, cooperative control, deployment recovery and stealth are described and summarized. The development trend of remote control, universal design, functional expansion and collaborative development are analyzed, and some references for the development of mine countermeasures in China are provided.

Cooperative Guidance Law of Multiple Aircrafts with Field-of-view Constraints

LIU Zhenyu, LIU Bingqi, WANG Jiping, YANG Chunwei

2022, 43(S2):  71-77.  doi:10.12382/bgxb.2022.B001

Asbtract ( )   PDF (3526KB) ( )  

References | Related Articles | Metrics

A distributed cooperative guidance law is proposed to solve the problem of multiple aircrafts cooperatively attacking a stationary target with field-of-view constraints. Firstly, the nonlinear motion model is transformed into a second-order agent model through the motion equations for engagement in the velocity coordinate system, and the field-of-view constraints are transformed into agent velocity constraints. Combined with the velocity constraint consistency protocol, an arrival time cooperative guidance law is designed to realize the cooperative attack of multiple aircrafts with field-of-view constraints. The proposed guidance law overcomes the problem of numerical singularities in the traditional cooperative guidance law, and there is no need to switch the guidance law in the cooperative process. Finally, through numerical simulation and comparative study, the effectiveness of the proposed guidance law is verified, which still has stable guidance performance in the presence of measurement noise and communication delay.

LSTM Intelligent Trajectory Prediction for Hypersonic Vehicles Based on Attention Mechanism

YANG Chunwei, LIU Bingqi, WANG Jiping, SHAO Jie, HAN Zhiguo

2022, 43(S2):  78-86.  doi:10.12382/bgxb.2022.B002

Asbtract ( )   PDF (5830KB) ( )  

References | Related Articles | Metrics

The near-space hypersonic vehicle has a non-inertial trajectory form and large-scale and strong maneuvering penetration capabilities.The accurate prediction of the target's flight trajectory can provide strong technical support for the effective interception of the missile interception system.To address the problem of glide and skiptrajectory prediction of hypersonic aircrafts, this paper proposes a Seq2Seq trajectory prediction model based on attention mechanism, which employsthe LSTM network to design the encoder and decoder, and uses the information extracted by attention mechanism to performdecodingand prediction. The network takes the six-dimensional feature sequence of the target trajectory's position, velocity, trajectory inclination angle and attack angle as the input network, and the continuous trajectory sequence during a certain period in the futureis the network output. The trajectory data of the target aircraft obtained by the trajectory simulation model is used as the training setto train and optimize the network. The experimental results show that the proposed network can effectively predict the various flight trajectories of hypersonic aircrafts with small prediction errors, which can provide some insights into the missile interception system.

Cooperative Combat Effectiveness Assessment of High-Power Microwave Weapons and Medium- and Short-Range Air DefenseWeapons Based on Fuzzy Wavelet Neural Networks

LI Ye, ZHENG Chun, TENG Zhe， GU Xiaodong, LUO Rong, XIN Zeyu

2022, 43(S2):  87-96.  doi:10.12382/bgxb.2022.B005

Asbtract ( )   PDF (2023KB) ( )  

References | Related Articles | Metrics

To improve the air defence capability of ships at sea, and to meet the challenges brought by the development of weapons and equipment technology, a research method was proposed based on the cooperative combat effectiveness of high-power microwave weapons (HPM) and medium- and short-range air defence weapons. The network was trained with the pre-processed data, its effectiveness was evaluated and the contribution rate of the HPM system was calculated after convergence. The results showed that the incorporation of HPM can improve the effectiveness of medium- and short-rangeair defence weapons and enhance the ships' overall combat capability.

An Adaptive Distributed Cooperative Guidance Strategy for Projectile Clusters in Complex Combat Environment

JIANG Shang, CHEN Feng, GAO Weipeng, LI Jinjun, SUN Dongyan

2022, 43(S2):  97-106.  doi:10.12382/bgxb.2022.B023

Asbtract ( )   PDF (3656KB) ( )  

References | Related Articles | Metrics

An adaptive distributed cooperative guidance strategy is proposed to improve the penetration ability and damage effect of shipborne gun guided projectiles, and to enable multiple projectiles to organize and cooperate in complex combat environment by themselves. An extended state observer with fast and accurate observation performance is designed to overcome external interference and constraints in the measurement of line of sight and angular velocity caused by the spin of projectiles. To address the problem of uncertain communication delay, a distributed controller in the direction of the line of sight is designed based on the cooperative consistency theory and integral sliding mode, which could converge the attack time within a limited time period. To eliminate the tracking error of the line of sight angle and line of sight angular rate in a certain time period, adaptive controllers using a nonsingular terminal sliding mode are installed along the normal and lateral directions of the line of sight based on the remaining flight time. Based on the Lyapunov theory and the Lyapunov-Krasovskii functional, it is proved that system is uniformly and ultimately bounded. Compared with existing research, experimental results reveal that this strategy improves the cooperative guidance performance of a projectile cluster against moving targets in a complex combat environment.

Life Cycle Cost Analysis and Control Strategy of Missile Weapons

LEI Liang, ZHOU Danfa, ZHANG Ying, GU Cunfeng, LIU Rui

2022, 43(S2):  107-114.  doi:10.12382/bgxb.2022.B009

Asbtract ( )   PDF (1948KB) ( )  

References | Related Articles | Metrics

With the advancement of science and technology, all kinds of weapons and equipment are becoming more and more advanced, and meanwhile their development, production, utilization and maintenance costs are increasingly higher. To deal with the high cost problem of missiles, this paper investigates and summarizes the relevant cost analysis and control methods at home and abroad, analyzes the life cycle cost of missile weapons and equipment, and puts forward the comprehensive strategy of the life cycle cost control for missile weapons as well as the idea of balancing efficiency and cost. Specific methods and measures are proposed to reduce the cost from three main aspects: overall scheme design, optimization of component selection, and production and manufacturing. This paper can provide some insights into the research on manufacture projects of weapon and equipment cost analysis and control.

3D Ship Model Generation Algorithm Based on Deep Learning

WANG Xiaoqi, ZHAO Yang, ZHANG Jian, WANG Shuo

2022, 43(S2):  115-119.  doi:10.12382/bgxb.2022.B011

Asbtract ( )   PDF (2662KB) ( )  

References | Related Articles | Metrics

The 3D ship model has a wide range of application scenarios, but its production cost is high. We propose an automatic generation method of 3D ship model based on deep learning: corner points are extracted from a 2D plan with the convolution neural network structure; each corner point is formed into a line segment according to specific rules, and each line segment represents a wall; the line segments are transformed to generate the 3D model; 500 2D ship diagrams are made for model training, and 30 2D ship diagrams for testing. The results show that the new algorithm can accurately detect the corner positions and types of the input image, and generate clear, beautiful and universal 3D models, and the test results demonstrate that the proposed method is effective.

Design of Boundary Alert System for Ship Navigation on Boundary River

LIU Yuesheng, ZHANG Shaorong, ZHU Chengpeng, ZHANG Wenshuan, ZHANG Chengzhi

2022, 43(S2):  120-125.  doi:10.12382/bgxb.2022.B014

Asbtract ( )   PDF (2331KB) ( )  

References | Related Articles | Metrics

In practice, persons on duty always analyze whether a watercraft has crossed the boundary by visual observation and experiential judgment, while in severe weather conditions or in broad stretches of the river where navigational aids are not properly distributed, the above-mentioned methods have potential safety hazards. It is necessary to use the navigation-aid alarm system to assistant with decision-making. By integrating three subsystems of positioning, identification and alarm, the Beidou Navigation Satellite System and GIS systems are integrated, network map resources are rationally used, the alarm area databased is established, and the plumb line method and CalcIntersectPoint function are used to recognize and judge the status of the ship. This paper introduces the features and design ideas of the boundary alarm system for ship navigation on the boundary river, clarifies the process of manufacturing and realizing the system, and verifies and analyzes its performance. The results show that the realization of the alarm system can provide some theoretical, technical and data support for the further development of the boundary alarm system for ship navigation on the boundary river.

Design of Distributed Destruction-Resistant Routing Algorithm for Space-Based Self-Organizing Network

GAO Zhao, WANG Yaqiong, ZENG Junjie, REN Shubo, ZHANG Lei, GAO Zihe, TAO Ying

2022, 43(S2):  126-132.  doi:10.12382/bgxb.2022.B018

Asbtract ( )   PDF (1847KB) ( )  

References | Related Articles | Metrics

The space-based self-organizing network is a complex network with large space-time scale, which has the characteristics of numerous nodes, complex composition, and high dynamic change of inter-satellite topology. To ensure the continuity of network information transmission, it is urgent to design a space-based ad hoc network routing protocol that can minimize the occurrence of rerouting and respond timely and accurately to network failures, thus minimizing the resulting losses. To deal with the problems of large delay and high packet loss rate in the source-end rerouting method used by the existing satellite routing algorithms, this paper proposes a distributed destruction-resistant routing algorithm for the space-based self-organizing network to minimize the end-to-end time. The optimal path is solved for the constraints, and a path to the destination node can be re-detected at the failed node by the break-point continuingly transferring method. The simulation results show that in the scenario where the node may fail, the algorithm can obtain better data transfer rate and delay performance at the cost of a small amount of control overhead, ensuring the reliability and invulnerability of routing.

Satellite Cooperative Formation Method Under the Same Time-Varying Delay Condition

ZHANG Jianku, WANG Di, WANG Rui, ZHANG Longfei, ZHANG Zeyu

2022, 43(S2):  133-138.  doi:10.12382/bgxb.2022.B017

Asbtract ( )   PDF (3008KB) ( )  

References | Related Articles | Metrics

In the task of satellite cooperative formation, the satellite cooperative formation communication is limited by the communication bandwidth. To address the problem of cooperative formation of satellites under the condition of communication delay, by combining the constraints of limited bandwidth of satellite cooperative communication in cooperative formation, the satellite communication system is designed with a dual redundant communication information transmission mode mainly based on position and speed information. The controllability of the satellite cooperative system under the time delay conditions is analyzed by using the matrix method, and the influence of the dual redundant communication information transmission mode on the stability and convergence speed of the cooperative system is investigated. Finanly, based on the stable convergence of the communication delay system, a simulation example is designed to verify the effectiveness and stability of the proposed cooperative formation method under the time delay situation. The results show that the communication delay system constructed with the dual redundant communication information transmission mode based on position and speed converges stably, and the simulation results verify that the position of the satellites in cooperative formation converges rapidly and stably, and the speed quickly becomes consistent, forming a “straight line” formation.

Intelligent Design System of Satellite Equipment Based on Digital Twins

DAI Lu, SHAO Yifu, GUO Yuyuan, XU Zhihong, ZHAO Qi, ZHANG Bing, DU Deyan, LIANG Tian

2022, 43(S2):  139-145.  doi:10.12382/bgxb.2022.B010

Asbtract ( )   PDF (3957KB) ( )  

References | Related Articles | Metrics

During the “14th Five-Year Plan” period, the number of satellite equipment development tasks is increasing year by year, and the satellite equipment becomes increasingly more complex. To improve the traditional way of designing satellite equipment based on experience and solve the problems such as low standardization of satellite equipment design database, poor data inheritance, poor data life cycle coverage, low interaction rate between production test/operation data and original data, which results in low design efficiency, high development cost, and difficult maintenance and upgrading, this paper proposes an intelligent design method for satellite equipment based on digital twins. According to the size, load and characteristics of satellite equipment, the database consisting of satellite load conditions, satellite equipment function modules, production inspection and test modules, and operation and maintenance modules is summarized. According to the satellite size, interface, load and other conditions, the twin satellite equipment digital function module is driven according to the calculation rules, and is automatically assembled into a twin model. According to some special conditions of the load, the digital twin model function module is intelligently adjusted, and the twin model calculation results, equipment physical verification results and the current twin digital model can be compared, iterated and modified to continuously improve the accuracy of the twin digital model. Through the twin model full life cycle data monitoring, the physical maintenance and transformation information can be synchronously mapped to the twin model in real time, which further improves the design efficiency of satellite equipment, shortening the development cycle and reducing the development cost.

Trajectory Design and Simulation for Asteroid Defense Based on Continuous Small Thrust Transfer

LIU Hao, DONG Yue, YANG Qian, LIU Jia

2022, 43(S2):  146-152.  doi:10.12382/bgxb.2022.B003

Asbtract ( )   PDF (3465KB) ( )  

References | Related Articles | Metrics

More and more asteroids have been discovered. In order to prevent their collisions with the earth, many researchers at home and abroad have conducted research on kinetic impact defense technology, and some on the optimization design of kinetic impactor for the asetroid Apophis based on pulse transfer. The continuous small thrust direct transfer is used to design and simulate the trajectory of the kinetic impactor for Apophis. The results show that the impactor using continuous small thrust direct transfer has low sensitivity to the earth's position at the time of launch, and the flight time on the optimal transfer trajectory under all windows is close to the maximum allowable flight time. At the time of impact, the orbital phase of Apophis is on the perihelion side because the orbital velocity of Apophis is high, which it is conducive to obtaining a large impact velocity. By comparing the design results of small thrust direct transfer and the pulse direct transfer, the Δv of Apophis is about 1.78 times of that of the pulse transfer.

Design of Nitrogen Filling System of Launch Canister Based on SSA-PID and Kalman Filter Control

LI Guangbao, GAO Dong, LU Yong, PING Hao, ZHOU Yuanyuan

2022, 43(S2):  153-163.  doi:10.12382/bgxb.2022.B013

Asbtract ( )   PDF (4420KB) ( )  

References | Related Articles | Metrics

To address the problems such as inconvenient operation and difficulty in the accurate control of nitrogen pressure in the current process of nitrogen filling and replacement for launch canisters, and to meet the requirements of nitrogen filling and replacement for launch canisters in remote and harsh environments, an automatic nitrogen filling system based on sparrow search algorithm (SSA)-PID and Kalman filter control is designed. The system takes PLC as the core and adopts the Kalman filter to filter the temperature, humidity and pressure parameters. SSA is used to optimize the parameters of the improved PID algorithm, and then the optimized improved PID control algorithm is employed to complete the control of the nitrogen filling process and the replacement process. Finally, the host computer is utilized to monitor and control the components in the system through MODBUS RTU bus communication, thus realizing the automatic and accurate operation of the nitrogen filling system. The MATLAB simulation and application results show that the nitrogen filling system of launch canisters based on SSA-PID and Kalman filter can improve the working efficiency and quality of launch canister maintenance, realize the functions of manual and automatic working modes, fault alarm and data recording, and meet the requirements of nitrogen filling and replacement for launch canisters in harsh environment.

Application of Reinforcement Learning in Decision-Making Management of Intelligent Unmanned System

WEI Ning, WANG Guan

2022, 43(S2):  164-169.  doi:10.12382/bgxb.2022.B012

Asbtract ( )   PDF (1413KB) ( )  

References | Related Articles | Metrics

Intelligent unmanned systems are required to make decisions quickly and stably in complex environments and have the ability to deal with unexpected states, but due to the high complexity of environment and tasks, it is often difficult for them to implement decision-making management. The reinforcement learning platform can provide a good solution to this problem. In view of the diversity, complexity, high dynamics and uncertainty of the environment in which the intelligent unmanned system is located, the decision-making management is carried out by using the reinforcement learning platform, and the environment and situation are accurately perceived and decided in the case of limited sensors, so that the agents can use self-learning and adaptive capabilities to quickly make decisions. Reinforcement learning learns the decision-making strategy through the autonomous interaction with the environment, so as to maximize the long-term cumulative reward value of the strategy. Through the connection of the reinforcement learning platform and the simulation platform, decision-making model construction and agent training are performed, and the decision-making management of intelligent unmanned systems is realized through the control of agent output strategy.

Data-driven Heat Treatment Technology for Spacecraft Products

YANG Xin, WEN Qiangmiao, LI Sizhen, CHENG De, SHU Wenxiang, BAI Jingying

2022, 43(S2):  170-177.  doi:10.12382/bgxb.2022.B016

Asbtract ( )   PDF (5962KB) ( )  

References | Related Articles | Metrics

The number of spacecraft development tasks is growing rapidly, and tend to have the features of mass production, rapid response, flexible customization. However, the traditional heat treatment for spacecrafts is mainly done by manual operations and manual data inspection and recording. There are problems such as poor digitalization of production equipment, poor timeliness, accuracy and integrity of process data, and lack of big data analysis. With a focus on the research on data-driven modular process technology, modular process design and implementation are performed. Based on the research on the digitalization of production equipment for heat treatment and independent health management technology, digitalization equipment and process technology are studied. By means of automatic collection and integration of production data and research on big data analysis technology, we conduct research on automatic collection and integration of data, quality problem analysis and decision-making to realize the digitalization of heat treatment production equipment, digital control of heat treatment production process, automatic data collection and big data analysis of heat treatment process, with the aim of realizing the informatization of special processes, and significantly improving the essential heat treatment production capacity of aerospace products.

Effect of Thermal Conditions on Properties of 7B04 Aluminum Alloy

LIU Wenyi, CHEN Fulong, WANG Yaoqi, QU Haitao, HAN Yujie

2022, 43(S2):  178-182.  doi:10.12382/bgxb.2022.B007

Asbtract ( )   PDF (2685KB) ( )  

References | Related Articles | Metrics

To address the forming difficulty of high-strength aluminum alloy aviation complex components, the effect of thermal conditions on the hardness and formability of 7B04 aluminum alloy was explored through resistance furnace heating and stamping and forming experiments. The mechanism was investigated using differential scanning calorimetry (DSC) and transmission electron microscopy (TEM). The results showed that: the faster the heating rate, the faster the hardness of 7B04 aluminum alloy decreases; when heating at the furnace temperature 400~600 ℃, within several minutes, the hardness first decreased and then increased; in the range of 200~450 ℃ of material temperature, the formability of 7B04 aluminum alloy improved with the increasing temperature; when the material temperature reached 400~450 ℃, the 7B04 aluminum alloy had the best forming effect. Therefore, a faster heating rate can make the 7B04 aluminum alloy reach a higher forming temperature with the same hardness drop, achieving better formability.