This paper proposes a unified dynamic modelling method for the rigid-flexible coupled robots that have variable topology. Furthermore, a global simulation method covering all the phases during the transformation from one topology to the another one, is also put forward. The proposed modelling and simulation method can be applied for both single and multi-robots transformation for vast on-orbit manipulation missions. First, a configuration parameter is presented that contains vital information on the topology configuration. An autonomous generation method of topology configuration description matrix for multi-arm spacecraft is also proposed. Secondly, a unified recursive kinematic modelling method and a general rigid-flexible coupling dynamic modelling methodology based on spatial operator algebra are described using configuration parameters. Then, a global simulation method that can be applied in both single and multi-robots operation scenario is presented to deal with abrupt changes in the state of motion. Finally, several topology simulations for rigid-flexible coupling multi-arm space robots are presented to verify the proposed method. These simulation results show that the methods can deal with several different topology scenarios while avoiding constraint violation problems.
Threat assessment is vital for air defense of warship, as it significantly improves decision making. Aiming at the problem that the uncertainty and combat intention of the target is not considered in the process of threat assessment for air defense of warship, a threat assessment method based on the variable weights intuitionistic fuzzy technique for order preference by similarity to ideal solution (TOPSIS) is proposed. Considering the inherent attributes and spatial situation of air targets, the threat assessment index system is established. Aiming at the uncertainty problem in the process of threat assessment, the method of transforming indexes into intuitionistic fuzzy sets (IFSs) is proposed. The objective weights and subjective weights are calculated based on intuitionistic fuzzy entropy (IFE) and combat intention, respectively. By minimizing the distance to the objectivity and subjectivity simultaneously, the calculation method of comprehensive variable weights based on the least square is proposed. An example show that the proposed method can give accurate threat degree and ranking of targets. Compared with other algorithms, it is shown that the proposed method can fully exploit the influence of the inherent attributes and spatial situation and give more reasonable results according to the target combat intention.
With the transformation of user demands in knowledge economy era, traditional knowledge service operation paradigm and implementation countermeasures cannot meet the demand of users. The previous research on knowledge service system is rich in theoretical content, but most of the research only stays on the shallow analysis of the concept and features. There is lack of information available to the construction of knowledge service system framework in details, especially in the academic area. This paper first contributes to the existing body of knowledge service solution, and then combines general knowledge service solution with integrated definition function (IDEF0) models to produce a knowledge service system framework. These IDEF0 models depict the hierarchy within knowledge service purposes and reveal strategies of meeting user demands in academic research. Finally, a prototype system in knowledge service system shows that the proposed framework can provide effective knowledge service for users, which will help to promote quality and satisfaction in knowledge service process.
This paper investigates a specific operational amplifier to overcome the limitations of traditional accelerated degradation testing, particularly issues related to limited data availability and inaccurate modeling. A particle swarm optimization algorithm is employed to design an optimal testing strategy that achieves a balance between model precision, reliability evaluation confidence, and cost-effectiveness. Utilizing the degradation data derived from experimental procedures, a time-scale function is incorporated into the Wiener process to model the nonlinear degradation behavior of the operational amplifier, accounting for the substantial randomness in environmental influences and the uncertainty associated with actual usage conditions. Furthermore, this study proposes a multivariate performance degradation modeling approach utilizing Copula functions to address product failures arising from competing performance parameters. Compared to conventional multivariate normal models, the proposed approach offers distinct advantages in accurately capturing complex nonlinear dependencies among performance parameters, streamlining the modeling process, and improving both flexibility and applicability. In the presented case study, an optimized reliability testing procedure is applied to a specific operational amplifier, followed by degradation modeling and reliability evaluation utilizing the proposed methodology. The results demonstrate that this integrated approach achieves 14.2% cost reduction, providing engineers with a practical framework for designing cost-effective testing programs without compromising assessment accuracy. The proposed methodology not only advances degradation modeling techniques but also offers direct economic benefits for industrial reliability testing applications.
Unmanned platforms, performing various tasks in urban environments, have garnered significant attention. This paper primarily focuses on analyzing and modeling the influence of various urban environmental factors on the unmanned platforms’ core competencies, which include motion, perception, operation, and communication abilities. Initially, the paper delves into the urban environment’s geographical, meteorological, electromagnetic, and temporal factors, identifying and categorizing the typical elements into static and dynamic components. It further models the primary urban elements and elucidates their interrelationships. Then, the paper categorizes the types of unmanned platforms that are suitable for urban task execution. It identifies six fundamental components essential for describing the capabilities of these platforms: the perception, computing, motion, power, operation, and communication systems. Subsequently, the paper constructs an impact model by analyzing how typical urban environmental factors affect these six components. A unified analysis framework is proposed to assess the urban environment’s impact on the capabilities of unmanned platforms. Finally, the effectiveness of this framework is validated through path-planning tasks in various typical urban scenarios.
Flight mission segments are essential components of aero-engine flight mission profiles. Current recognition methods rely on manual processes, leading to inefficiencies and inaccuracies in aero-engine load analysis. To solve this problem, this paper presents an automatic method for recognizing flight mission segments using bidirectional recurrent neural network (Bi-RNN). Initially, the decomposition of flight mission profiles, manual division of mission segments, labeling of mission segment, and the establishment of maneuver sequence table are introduced, respectively. Secondly, the automatic recognition models are constructed using bidirectional long short-term memory (Bi-LSTM) and bidirectional gated recurrent unit (Bi-GRU). By collecting measured load data from a third-generation aero-engine, including 50 low maneuvering and 50 complex maneuvering flight mission profiles, the dataset is set utilizing K-fold cross-validation and the sliding window method. The optimal parameters for the models are determined through training, and their recognition performance is assessed. The results indicate that the Bi-RNN model achieves over 80% accuracy in recognizing flight mission segments in both low and complex maneuvering flight mission profiles. As a result, the flight mission segment automatic recognition method presented in this study allows for more efficient and precise aero-engine load analysis, which is of great significance for aero-engine life evaluation research.
Previous studies have paid limited attention to the critical role of unmanned aerial vehicle (UAV) altitude variation in determining three-dimensional (3D) search efficiency. To address this gap, this paper introduces a deep reinforcement learning framework integrated with adaptive matrix optimization in multi-UAV target search. The proposed framework explicitply models altitude variations’ impacts on observation range and detection accuracy. To balance flight safety, coverage, and detection precision, deep Q-network (DQN)-altitude matrix optimization (AMO) discretizes 3D trajectories into horizontal paths and vertical altitude decisions, effectively reducing the problem dimensionality. Furthermore, a curriculum learning approach is employed to decompose the search process into phased sub-tasks, each with customized decision rules and reward mechanisms. This hierarchical strategy accelerates agent learning and enhances performance in complex scenarios. Comprehensive experimental evaluations in simulated environments demonstrate that the proposed DQN-AMO outperforms benchmark methods in both robustness and generalization.
The survivability of the infrastructure network, especially the combat system, is a core index to reflect the merits of the system. The cascade effect caused by the failure of a single or a few nodes is the focus of the research on the resistance. Many scholars have studied this problem and put forward some useful cascading failure models. Considering node resilience, a cascade failure model is proposed in which nodes have three states: normal, overload and failure. In addition, the conditions for the failure of connected edges are given. The model fully considers the redundancy design of the real system, and can objectively reflect the performance of the system to deal with cascade failure. We study the effect of node resilience on network cascade failure in both typical network and real network. Experimental results show that the proposed model can reduce the scale of cascade failures with higher cost utilization compared with the classical model that is widely used, especially when the network capacity is small.
The missiles typically require multiple stages tests to improve hit accuracy. The existing estimation methods seldom consider the tests characteristics of multiple stages growth of missile hit accuracy, which bring difficulties to accurately estimate the missile hit accuracy. Considering the different degrees of damage caused by missile hitting the target in different areas, the Dirichlet distribution is selected as the prior distribution of hit accuracy parameters based on the Bayesian method. The sequence constraint relationship between the hit accuracy parameters of each stage test is established, and the Bayesian estimation model of hit accuracy based on multiple stages growth tests is constructed. The Markov chain-Monte Carlo method combined with Gibbs sampling is used to overcome the problem of solving the posterior high-dimensional integral of the model to complete the model solution. The example shows that this method can fuse multiple stages growth tests information compared with the existing single stage test method, which can provide reference for the estimation of missile hit accuracy during the period of research and development.
In order to provide low Earth orbit (LEO) satellite network survivability with limited resources, and effectively respond to the risk of on orbit operation, a survivable routing algorithm based on multi-agent reinforcement learning is proposed. The reinforcement survivable routing establishes the reward function from the perspective of network utility, and describes the improvement of survivability in the failure scenario as a joint optimization problem, which solves the online routing decision-making problems after LEO satellite network failure. Each cognitive user agent and satellite agent can independently determine the routing strategy for communication missions according to the time slot topology, node survival status, storage space and other environment information of the satellite network. The simulation results show that compared to the weighted semi-distributed routing algorithm (WSDRA) and Fibonacci multipath load balancing (FMLB) algorithm, the proposed multi-agent double deep Q-learning network (MADDQN) reinforcement survivable routing algorithm can adapt to satellite failure and topology changes, and improve network utility by 14% and 9% respectively in human attack scenario, and by 17% and 13% respectively in random failure scenario.
Validation for simulation models often confronts challenges with small samples due to the costs of time and money. To address this issue, this paper presents a validation method for small-sample dynamic outputs based on Gaussian process regression (GPR) models. Firstly, a validation framework based on Bayes statistics is proposed, shifting the focus from merely analyzing validation data to a more comprehensive analysis of posterior distributions. Subsequently, the posterior distributions of both the simulation outputs and the reference data are separately captured through segmented GPR. Then, the consistency of these posterior distributions is evaluated in terms of the central tendency and the distribution range. This consistency serves as a quantitative measure of the simulation model’s credibility, expressed as a value ranging from 0 to 1, where a value closer to 1 indicates higher credibility. Finally, the effectiveness of this validation method is demonstrated through a numerical example and an application example, highlighting its capability in uncertainty description and adaptability to small samples.
This research proposes an odd-even dimension RUNge Kutta algorithm (ODRUN) to solve global optimization and a well-known NP-hard problem in inventory management. The rpoposed algorithm integrates odd-even dimensional, fourth-order Runge-Kutta method, and neighbor search strategies. This hybrid approach significantly improves population diversity, avoids local optima, and enhances convergence accuracy. To validate the performance of the proposed algorithm, a widely recognized benchmark function suit from CEC2022 is first employed. Results confirm that ODRUN achieves an overall effectiveness ratio of 66.67% across three statistical indicators (best, mean, and standard deviation) for 12 benchmark functions. The test shows this algorithm is ranked first compared to seven state-of-the-art metaheuristic algorithms. Furthermore, ODRUN is applied to the joint replenishment problem with imperfect items and trade credit. Numerical examples from 600 randomly generated large-scale instances highlight that the algorithm’s performance remains unaffected by an increase in problem scale. The significant cost savings brought by the ODRUN algorithm, with the maximum improvement ratio in average cost and best-found total cost ranging from 14.81% to 19.5%, are achieved in comparison to other algorithms. In conclusion, ODRUN is an effective and robust tool for complex optimization problems.
To address the energy consumption issues caused by task lengths in task scheduling on heterogeneous multi-core systems, this paper proposes an adaptive parameterized improved simulated annealing algorithm based on the directed acyclic graph task model. The algorithm employs feedback from acceptance rates to dynamically adjust the temperature and neighborhood size of the simulated annealing process. Additionally, it introduces a security mechanism to enhance convergence speed and global search capabilities. Compared against classical simulated annealing and standard heuristic algorithms, the proposed algorithm achieves reductions exceeding 54% in convergence generations, 50% in task slots, and 10% in scheduling time, providing a direction for low-power task scheduling.
Integrating prognostics and health management (PHM) with the existing maintenance support system of systems plays an important role in implementing reliability-centered maintenance (RCM). However, the increasing complexity and integration of civil aircraft systems pose challenges for conventional document-based systems engineering (DBSE) practice. Aiming at the specific problems of poor modeling degree, weak traceability between problem and solution domains, and insufficient integration in civil aircraft PHM development, a model-based systems engineering (MBSE) approach is adopted to overcome the limitations of DBSE method. This paper proposes a structured integrated modeling method to facilitate PHM functional integration with other aircraft systems. An MBSE modeling method based on traceable requirements, functional, logical, and physical models, is applied in the integration process. Additionally, a multi-viewpoint analysis method within the Department of Defense Architecture Framework (DoDAF) is introduced to illustrate the modeling elements and processes from a multi-dimensional perspective. The modeling logic and architecture are subsequently presented, followed by examples of requirements, functional flows, and resource flows models using the systems modeling language (SysML). Finally, a preliminary logic simulation verification is conducted as a case study of typical PHM functional integration with maintenance support. The case study results demonstrate that the proposed method enhances information traceability and consistency, which can offer theoretical support and technical reference for the development of maintenance support system.
Existing weapon portfolio selection methods do not sufficiently support specific combat tasks, with uncertainty in the decision information. Therefore, a combat task–oriented weapon portfolio selection method that adapts weapon capabilities to combat tasks is proposed. The approach is based on specific combat tasks and weapon background, using fuzzy interval values to describe indicators and the applicability of a weapon portfolio. In addition, an interval entropy weighting method is applied to obtain weight information of indicators. Meanwhile, we define the similarity measure of fuzzy interval values and use the interval fuzzy collaborative filtering algorithm to calculate the fitness of the residual weapons. Furthermore, the interval fuzzy set clustering algorithm clusters the tasks to inform the decision of weapon portfolio. Finally, we verify the method’s feasibility and advancement by comparing actual combat tasks as examples with the traditional methods. The contributions of this paper include improvements to the accuracy and reliability of decision-making from the perspective of adapting weapon capability to combat tasks. At the same time, this paper accounts for the method’s shortcomings by considering the hesitancy and ambiguity of the indicator data.
Remote sensing satellites (RSS) are highly complex and customized from a common product family. It makes the traditional model-based system engineering (MBSE) method, which lacks architecture-level reusability, difficult to apply to their architecture design. Considering RSS has a relatively fixed common architecture from which the various design solutions are customized specific to different missions, the model-based product line engineering (MBPLE) methodology can be leveraged. In this paper, based on the analysis of the current RSS development process in practice and the main issues of current MBPLE methods, an RSS-specific MBPLE approach is proposed. Firstly, the RSS domain terminology is consolidated into the RSS-MBPLE SysML profile to support the construction of models in the design process. Then, the two key steps, i.e., architecture configuration and standalone product selection are efficiently conducted following the MBPLE principles supported by plugins of the mainstream SysML platform. Finally, a typical RSS control subsystem is illustrated as the case study to demonstrate the effectiveness of the proposed method. The results show that the proposed approach improves architecture-level reusability and design automation compared with traditional methodology, thereby reducing manual clone-and-modify efforts and enhancing the efficiency of RSS architecture design.
The implementation of timely monitoring and preventive maintenance plays a fundamental role to ensure the reliable operation of complex systems. Condition-based maintenance strategy offers an effective means to leverage system remaining life information, enabling the application of targeted measures to reduce maintenance costs and elevate overall operational efficiency. This study delves into a performance degradation system affected by external random shocks, utilizing the Wiener process model to characterize the continuous degradation process. Within this framework, two distinct condition-based monitoring schemes are proposed: one is the real-time condition monitoring and the other is the dynamic periodic monitoring. Through the optimization of maintenance strategies for each scheme based on the long-term average cost, the study aims to optimize the preventive maintenance threshold for system failure. The Monte Carlo simulation algorithm is adopted to solve the optimization problem. Finally, a comprehensive numerical example is provided to validate the efficiency of both the models and the proposed maintenance strategies.
Forest fires are characterized by their abrupt onset and highly destructive nature, resulting in significant annual property losses. Hence, regular surveillance is imperative for forest fire prevention and mitigation. The fundamental challenge in patrolling is akin to the problem of helicopter route planning. Conventional unmanned aerial vehicle (UAV) path planning commonly entails single-trip missions. Considering the extensive and complex forest environments, we advocate a multi-stage UAV reconnaissance strategy to address the daily inspection route planning conundrum. This approach facilitates UAVs to conduct round-trip flights between designated surveillance points and the base station at diverse time intervals, effectively satisfying the requirements for multi-tiered, hierarchical reconnaissance. Furthermore, we develop an advanced multi-strategy genetic algorithm (MSGA) to optimize the multi-stage reconnaissance model. Experimental outcomes underscore the superior performance of the enhanced MSGA, achieving a reduction of nearly 20% in total flight path length relative to the traditional genetic algorithm. This methodology significantly enhances the efficacy of daily forest patrols.
The evaluation of the equipment contribution rate to system-of-systems (CRSoS) is crucial for optimizing the armament system-of-systems structure and enhancing combat effectiveness. The traditional relative contribution rate method poses limitations by focusing on individual equipment evaluation without considering the interrelations between equipment. In response to the issue, this study proposes a framework based on operation loop and improved Shapley value (OLISV) for analysis to ananlyze the equipment CRSoS. Specifically, a multi-layer network model is first constructed based on complex heterogeneous network and operation loop theory. Next, information entropy and evidence theory are used for the edges of the functional node layer, while improving the parallel node structure within the network. Subsequently, an improved Shapley value contribution rate method based on non-efficiency influencing factors is proposed. Finally, the rationality and effectiveness of the OLISV are illustrated through a case study.
In this paper, the system we consider has multiple inventory warehouses and multiple pieces of equipment with multiple repairable components, where the joint planning of spare components and maintenance workers with lateral and cross-echelon transshipment is studied. Firstly, the characteristics of inventory system is analyzed, and the scheduled relationship of maintenance resources is carded. Based on this, a total system cost model is proposed, incorporating holding, ordering, and maintenance costs under an average waiting time constraint. A hyper-heuristic algorithm is then introduced to efficiently solve larger-scale problems with improved computational speed, and is applied to derive an optimized inventory allocation plan for maintenance resources. Finally, a maintenance system is analyzed, comprising four local warehouses, three central warehouses, and one plant that serves five machine groups. Each group contains four machines, each warehouse supports one or two machines, and every machine includes five independently failing key components. By analyzing the effect on reducing total cost, improving maintenance demand satisfaction rate, the effectiveness of the proposed optimization approach is verified.
The launch process of a multi-stage launch vehicle is significantly influenced by uncertain parameters, including air density, aerodynamic parameters, and engine thrust, which often exhibit deviation. Predicting the trajectory range of the launch vehicle under the influence of uncertainty is essential before launch, and uncertainty quantification serves as a crucial method to address this challenge. In traditional uncertainty quantification for launch vehicles, unknown parameters are often assigned specific distributions based on prior knowledge. However, prior knowledge is sometimes subjective, and unknown parameters are often assigned conservative ranges to meet safety margins. In addition, the flight data of the past launch is precious, especially in quantifying the uncertainty of reusable or same-type launch vehicles. This paper utilizes flight data to estimate parameters base on Bayesian methods and integrates the estimation results with prior knowledge, which can more objectively set the distribution of uncertain parameters. Reasonable distribution has a positive impact on uncertainty quantification, which can avoid control strategies that are not robust enough or overly redundant. Therefore, the uncertainty quantification for launch vehicles is discussed under different information sources. In addition, the algorithm is accelerated based on Gaussian process regression and polynomial chaos expansions.
To predict the ranking of the country’s innovation capability in the world in real-time, this study designs a two-phased prediction model based on the pairwise comparison. Data from the global innovation index (GII) reports are employed in this study. Countries with different income levels have shown different development inertias, the two-phased prediction model is thus proposed. In the first phase, the GII data from the previous year are applied to predict the ranking of innovation capability for high-income countries. In the second phase, more years of historical data are adopted to predict the innovation ranking for other countries. The global innovation rankings for all countries and economies are thus obtained. Experiments have proved that the model requires only a few indicators to get accurate results. The model provides real-time decision support for decision-makers to formulate innovative development policies.
Resolving conflict and achieving consensus among social groups with diverse opinions becomes a critical issue in today’s extensively connected society. Despite the ubiquitous heterogeneity of connection or contact patterns, the study of how topological characteristics of network structure affect opinion convergence is still insufficient. Based on Deffuant and colleagues’ bounded confidence model and the transformable network structure between random network and typical complex network types, including small-world network and scale-free network, we analyze the critical factors affecting continuous opinion convergence. We find that the network density plays a crucial role in the aggregated process of opinions in the social group, followed by the modularized level and the average shortest path length of the social network. However, the structural features have little impact on the consensus phase transition threshold. The further simulation experiments under real networks can be well understood based on the interplay of these three main factors. These findings confirm the paramount importance of creating a high-frequency and widely communicated atmosphere to mitigate conflict and efficiently reach consensus.
The evaluation of air combat decision-making has garnered significant attention due to its potential to effectively mitigate losses resulting from erroneous decisions. However, existing research primarily focuses on static evaluation methods. Therefore, this paper proposes a dynamic multi-round decision evaluation method based on the characteristics of multi-round unmanned aerial vehicle air combat under opponent’s optimal strategy. In order to determine objective weights, an improved multi-attribute decision making method is proposed, which incorporates the proximity as a correction coefficient for evaluation indicators, utilizing the cosine similarity instead of Euclidean distance, and incorporating both actual and theoretical objective weights to prevent data mutations. Subsequently, the game theory is employed to reasonably adjust subjective and objective weights to obtain comprehensive weights. To address the issues related to the ambiguity and randomness during the evaluation process, a reverse cloud generator is utilized to determine the center of gravity of the cloud model using comprehensive weights while employing the weighted deviation degree for evaluating air combat decision-making effectiveness. By activating the cloud generator through the cloud model, the optimal strategies for each round of air combat are determined, thereby completing the dynamic evaluations for multi-round sequential decision-making processes. Finally, the feasibility and effectiveness of the proposed method are verified through simulations.
Weapon target assignment (WTA) problem is a critical problem in multiplatform confrontation. This paper studies a static WTA problem with heterogeneous weapons in multi-platform air combat scenarios, called heterogeneous WTA (HWTA) problem. Heterogeneous indicates that the engagement platforms carry multiple kinds of weapons for different tactical purposes. The targets assigned and the weapons used by one side’s platforms will affect the survival probability and capability of the other side’s platforms. The goal of each side in HWTA is to find a solution to determine the kind of weapon used and the target assigned for each platform, so as to maximize their combat effectiveness. The problem is formulated as a two-player noncooperative game model with considering the conflicts between the engaged sides. The Nash equilibrium is an effective solution to the game in which no player has an incentive to deviate. However, the number of pure strategies in HWTA increases exponentially with the engagement platforms. To improve computing efficiency, a double oracle algorithm with constructive heuristic (DOCH) is developed, within which the constructive heuristic is embedded to solve the oracle subproblems efficiently. Numerical experiments are conducted to verify the effectiveness of the DOCH. The results show that the DOCH can find effective strategies for platforms to improve combat effectiveness. Moreover, the DOCH can find high-quality solutions in seconds, significantly outperforming the state-of-the-art algorithms in terms of computational efficiency, especially for large-scale problems.
Multi-domain competition is developing for disintegrating the component of the opponent’s operational system and winning advantage in decision space. Island air defense is a typical multi-domain security problem, which dramatically increases the complexity of decision-making by considering different factors such as multi-stages decisions, multi-domain settings, imperfection information, and uncertain events. However, current research on island air defense security problems is sparse and lacks consideration of key factors. To provide support for assisting human commanders to take wise decisions in a complex environment, we build a multi-domain multi-state island air defense model and propose responding solving algorithms. We study the whole progress of island air defense and propose a multi-domain, multi-stage imperfection information security game that formulates critical characters in the adversarial scenario of island air defense. In addition, considering a bounded rational opponent’s possible strategies, we propose an opponent-aware Monte Carlo counterfactual regret minimization algorithm for learning a robust defensive strategy in the security game. We evaluate our methods in various adversarial scenarios. The results show that our equilibrium learning method can effectively play against an opponent with bounded rationality and significantly outperform some advanced algorithms.
To address the problem of sea ice collisions threatening offshore drilling operations in polar regions, this paper proposes a Bayesian network–based collision risk assessment model for drillships. The model integrates large ice floe/iceberg conditions, natural environmental factors, and geometric factors derived from the ship’s shape, size, distance, and azimuth. Using iceberg routes, scenario simulations are conducted to evaluate collision probabilities and provide time-dependent risk values. Results demonstrate that the method yields reasonable and consistent assessments of drillship–ice interactions. The proposed method enables automatic collision risk assessment and can be applied to unattended management systems to enhance the safety of polar drilling operations.
With the improvement of the informatization and intelligence level of logistics equipment, the interactive and collaborative relationships between equipment entities become complex, and the uncertainty problems emerge in the equipment system-of-systems. Herein, a heterogeneous network model is built to describe logistics equipment system-of-systems, which considers the heterogeneity and complex connections of different logistics equipment nodes. Next, the topological structure properties of this model are analyzed. On this basis, the experiments on the logistics equipment system-of-systems under attack strategies including degree attacks, betweenness centrality attacks and random attacks are taken to assess the changes of structural invulnerability. Results show that the logistics equipment system-of-systems heterogeneous network has similar topological structure characteristics of typical complex networks, namely small-world effect and scale-free characteristics, indicating that the flow, sharing, and synchronization between logistics equipment entities in the network are relatively easy. Meantime, the key logistics equipment nodes with large values such as degree, closeness centrality, and betweenness centrality should be protected in the logistics equipment system-of-systems heterogeneous network against deliberate attacks. The current work provides a perspective for demonstration and affords the theoretical support for development and decision-making of logistics equipment system-of-systems.
To overcome the limitations of traditional force aggregation methods, this paper proposes a novel clustering model integrating the self-adaptive tent chaos search ant lion optimizer (SATC-ALO) and the self-organizing map (SOM) network. The model introduces a hybrid distance calculation method to measure inter-target distances and enhances the ant lion optimization algorithm through tent chaos sequences, adaptive tent chaos search, tournament selection, and logistic chaos sequences. Aggregation accuracy is evaluated using minimum quantization error and confidence value for the SOM neural network. The model is resolved using SATC-ALO and SOM independently, with experiments demonstrating that SOM achieves fast and accurate grouping, while SATC-ALO offers higher precision but requires longer computational runtime, making it more suitable for hybrid approaches. Both methods are validated as practical solutions for force aggregation tasks.
Deep reinforcement learning algorithms are revolutionizing intelligent decision-making in air combat, drawing widespread attention and extensive research. However, air combat agents trained with these algorithms face significant challenges, such as limited decision-making capacities due to adversarial training against relatively fixed and singular expert strategies, and a lack of interpretability and reliability in their decision-making processes. To tackle these issues, this paper proposes a self-play training mechanism based on policy switching and opponent selection, allowing air combat agents to refine their capabilities via engaging with previous versions of themselves. Additionally, an explainable decision tree model is developed to clarify the decision logic of these agents. Simulations and results demonstrate that the proposed self-play training approach significantly enhances the decision-making abilities of air combat agents, with late-stage agents showing a 38% improvement over early-stage agents in confrontations with an expert strategy. Moreover, the explainable decision tree model effectively elucidates the decision logic and achieves an 86% win rate against the expert strategy, comparable to the 88% win rate of the air combat agents.
