Journal of Advances in Engineering and Technology

Differential Dynamics Modeling and Simulation Analysis of Multi-Agent Cooperative Motion

2025-01-23T06:30:02+00:00

With the widespread application of multi-agent systems (MASs) in fields such as drone formations, autonomous driving, and robotic swarms, achieving efficient collaboration and stable motion among agents has become a key research focus. This study begins by describing the vertices of agents relative to the formation centroid to enable collision avoidance and formation shape tracking control. Using the Lyapunov direct method, a heat-equation-based collective dynamics model for multi-agent systems is established, providing stability criteria for the model and a leader-follower algorithm. The model enables the transformation from continuous multi-agent systems to discrete systems, completing the cooperative motion of real multi-agent systems. Simulation analysis verifies the effectiveness of the proposed model and control strategy. In a typical simulation scenario, follower agents achieve consensus with leader agents within approximately 10 seconds, with the number of path nodes reduced to just six, zero obstacle collisions, and a computation time of only 49.6 seconds. The proposed control method significantly enhances the cooperative efficiency and motion stability of multi-agent systems under limited information exchange and complex environmental conditions, offering robust theoretical support for the collaborative control of future intelligent systems.

Graph-Based Deep Learning for E-Commerce Fraud Detection

2025-03-24T03:19:16+00:00

E-commerce growth has fueled increasingly sophisticated fraud schemes, including transaction manipulation and payment fraud. Traditional fraud detection methods struggle to adapt, leading to high false positive rates and ineffective detection of emerging fraud patterns.

This study proposes a graph-based deep learning framework that models e-commerce transactions as a heterogeneous graph. It utilizes graph convolutional networks (GCN) and graph attention networks (GAT) for spatial fraud detection and temporal graph networks (TGNs) for tracking sequential fraud patterns. Semi-supervised and reinforcement learning mechanisms enhance adaptability to evolving fraud tactics.

Experiments on real-world datasets show that the proposed model outperforms traditional methods, achieving higher accuracy and lower false positives. Its effectiveness in detecting multi-step fraud rings and synthetic transactions underscores the potential of graph-based deep learning in securing e-commerce platforms.

Analysis on Intrinsic Vibration Characteristics of Disc-Lobe Coupling System of Marine Gas Turbine

2025-02-27T02:47:58+00:00

As the core component of the modern ship power system, the vibration characteristics of the rotor system are of great importance to the stability and reliability of the whole power system. With the development of lightweight and thin ship gas turbine, the traditional method of only considering the vibration of the blade under the root fixation is no longer applicable. Therefore, it is important to study the vibration characteristics of the wheel and blades as a coupled system. This paper aims to establish the analysis model of the vibration characteristics of the disc-lobe coupling system of Marine gas turbine, and analyze the influence of temperature and rotation speed on the vibration characteristics of the system. Through finite element analysis and experimental verification, this study provides a theoretical basis for the design and safe operation of ship gas turbine. In the process of analysis, this paper first introduces the theoretical basis of the vibration characteristics of the disk-lobe coupled system, including the vibration theory, finite element analysis method, cyclic symmetric structure algorithm, etc. These theoretical bases provide a scientific basis for the subsequent model building and computational analysis. Then, the calculation model of the disc-lobe coupling system of Marine gas turbine is established, and the cyclic symmetry analysis function and geometric nonlinear analysis function of NASTARN is used. In the model, the rotating centrifugal force and the material parameters vary with temperature are consideredinfluence. In addition, the paper verifies the accuracy of the calculation model, and summarizes the relationship between temperature, rotational speed and the intrinsic vibration characteristics of the disk-lobe coupling system. The calculated results and the measured data are also compared. The error sources of the model are analyzed and the practical significance of the experimental results for the design and operation of ship gas turbine is discussed. The results show that the vibration characteristic analysis model of disc-lobe coupled system considering the influence of temperature and rotation speed can provide theoretical support for the design and safe operation of ship gas turbine, and has an important engineering price for improving the reliability and safety of ship power system

The Nonlinear Mathematical Modeling and Optimization of Distributed Control in Complex Systems

2025-01-23T06:29:59+00:00

With the widespread application of complex systems in industries such as manufacturing, transportation, and energy, their high-dimensional, strongly nonlinear, and dynamically coupled characteristics pose significant challenges to traditional centralized control. To address these complexities more efficiently, this study constructs a nonlinear mathematical model by introducing nonlinear feature mapping into a multiple linear regression framework and implements distributed optimization using the Alternating Direction Method of Multipliers (ADMM). The proposed method is validated through the simulation of the nonlinear dynamic behavior of a deep-water riser–test pipe system, with experimental designs encompassing multi-dimensional vibration responses and dynamic environmental disturbances. The results demonstrate that the proposed nonlinear model significantly outperforms other methods in terms of prediction accuracy and optimization efficiency. Under varying amplitudes and frequencies of disturbances, the model achieves lower error rates and higher robustness, with an adaptation decay rate of less than 17.6%. These findings indicate that the proposed nonlinear modeling and distributed optimization approach can effectively capture the dynamic characteristics of complex systems, making it suitable for real-time distributed control scenarios with promising engineering applications.

Optimizing Cybersecurity Incident Response via Adaptive Reinforcement Learning

2025-03-24T03:26:21+00:00

Cybersecurity threats have evolved dramatically over the past few decades, requiring organizations to continuously improve their security posture. Traditional cybersecurity incident response (CIR) frameworks, which rely on predefined rules and heuristics, have shown significant limitations in addressing sophisticated and rapidly evolving cyberattacks. The increasing complexity of threat landscapes necessitates adaptive security mechanisms capable of learning and evolving in real time. This paper explores the potential of Adaptive Reinforcement Learning (ARL) as a mechanism to enhance cybersecurity incident response strategies. Reinforcement learning (RL), a subset of machine learning, is well-suited for dynamic decision-making scenarios, where optimal strategies emerge through iterative learning. By integrating adaptive RL techniques into CIR, cybersecurity professionals can develop response strategies that continuously refine themselves based on observed threats, attack vectors, and system vulnerabilities.

The study first examines conventional CIR approaches, discussing their constraints in modern cybersecurity environments. A comprehensive literature review explores the existing machine learning methodologies applied to cybersecurity and the emerging role of reinforcement learning in security applications. The methodology section presents the design and implementation of an ARL-driven incident response framework, detailing the algorithmic foundation, data sources, and training methodology. The effectiveness of the proposed approach is validated through extensive simulations across different cyberattack scenarios. Results highlight the superior performance of adaptive RL models in minimizing response time, improving threat mitigation rates, and reducing false positives when compared to traditional rule-based and supervised learning approaches.

In addition to analyzing the results, the paper discusses practical challenges in deploying RL-based cybersecurity frameworks, including computational overhead, adversarial learning risks, and the need for high-quality training data. Future research directions are explored, emphasizing the importance of integrating federated learning techniques, adversarial resilience mechanisms, and multi-agent reinforcement learning systems to further enhance cybersecurity defenses. This study contributes to the growing field of AI-driven cybersecurity by demonstrating how adaptive reinforcement learning can optimize decision-making processes in real-time incident response, ultimately paving the way for more intelligent and resilient cyber defense strategies.

Design and Application of a High-Dimensional Robust Control Chart for Joint Monitoring of Location and Scale Parameters

2025-02-27T03:10:06+00:00

In industrial production, statistical process control is a common method used to ensure process stability and product quality. With the development of production technology and the increasing complexity of products, the number of product index parameters that need to be monitored is also increasing, and the traditional control chart method often faces challenges in processing high-dimensional data. For example, the traditional control chart method is applied based on the assumption that the process data distribution is known, and the continuous data is usually assumed to be normally distributed, while many data in the actual process do not follow the normal distribution. Secondly, high-dimensional data often contains complex features, and there are often correlations between variables, which makes it difficult to describe the joint distribution of high-dimensional data. These problems will greatly affect the monitoring effect of the control chart. In view of the above problems and the characteristics of high-dimensional data, this paper first combines the score test statistics with the exponential weighted moving average (EWMA) method after mathematical transformation, and proposes a local statistic to monitor each one-dimensional data stream. Then the correlation between data streams is represented by the appropriate combination of marginal distribution functions, and the global statistics for monitoring high-dimensional data streams are constructed. The control chart proposed in this paper is different from the traditional control chart, it does not need to know the distribution of the process, and can monitor the position parameters and scale parameters simultaneously. The effectiveness and robustness of the control chart are verified by numerical simulation and example analysis.

A literature Review of Ant Colony Algorithm Based on Cite Space

2025-02-26T07:18:15+00:00

Ant colony algorithm is a kind of biological heuristic algorithm, which has been applied in the fields of combinatorial optimization, path planning, task scheduling and other fields and has achieved significant optimization results, so it is necessary to sort out the literature of ant colony algorithm and deepen the understanding of its research status, hotspots and future development directions. In this paper, the process, principle and application fields of ant colony algorithm are sorted out, and the literature related to ant colony algorithm is bibliologically analyzed based on Cite Space software, and the number of publications, the current situation of researchers and research institutions are summarized, and the research hotspots and trends of ant colony algorithm are revealed through citation network and keyword co-occurrence analysis. Through bibliometric analysis, we understand that the research on ant colony algorithm is stable, and there is overlap and integration with other optimization algorithms. Future research can continue to focus on the improvement and application of ant colony algorithm, and explore its combination with other algorithms to promote the application of ant colony algorithm in a wider range of fields.