This paper presents a novel deep learning-based architecture designed to improve multi-target tracking for UAV fire controlsystems. The proposed approach integrates a ResNet-50-based Convolutional Neural network (CNN...
详细信息
This paper proposes a direct data-driven approach to address decentralized control problems in networksystems, i.e., systems formed by the interconnection of multiple subsystems, or agents. Differently from previous ...
详细信息
Model predictive control is an emerging embedded control scheme that is increasing relevant to modern power systems. It is known to be capable of improving the stability and regulation performance of the power grid wi...
详细信息
This proposal consists of a system and a method of presence control without the need for any action on the part of the user. The system is able of detecting and registering users in an area. This action is performed t...
详细信息
ISBN:
(纸本)9783031775703;9783031775710
This proposal consists of a system and a method of presence control without the need for any action on the part of the user. The system is able of detecting and registering users in an area. This action is performed transparently to the users so that the system does not require interaction by the users or any other operator to be detected. This system is ideal for time-stamping in an organization. This system has significant advantages over current systems, because the presence control does not require the intervention or the performance of specific actions of the agents involved to carry out the process of presence detection and registration. The system can be applied in work environments of any type and size, regardless of the number of workers to be registered and supervised. It provides up-to-date information on the real-time registration of the organization's workers. It is compatible with existing systems and can be deployed to complement or replace them.
Emotional neural networks have gained attention in different fields. Despite their growing applications, their employment in more complicated control problems is not much investigated. Accordingly, in this study, we e...
详细信息
Microgrids are essential elements within the burgeoning energy Internet infrastructure. The synergy of communication networks and controlsystems facilitates the development of intricate microgrid management strategie...
详细信息
ISBN:
(数字)9798350379228
ISBN:
(纸本)9798350390780;9798350379228
Microgrids are essential elements within the burgeoning energy Internet infrastructure. The synergy of communication networks and controlsystems facilitates the development of intricate microgrid management strategies;however, this integration also opens the door to various forms of interference. Moreover, inadequate primary control can lead to discrepancies between the actual frequency and voltage of the microgrid and their desired reference values, as well as imprecise distribution of active and reactive power. To tackle these challenges, an integral sliding mode-based quadratic control strategy is proposed. This tactic utilizes sparse communication with neighboring distributed power sources, thereby streamlining the complex communication network structure. It diminishes deviations caused by individual controls and counteracts the system's disturbance effects. Simultaneously, a finite-time consensus protocol is incorporated with the integral sliding mode control, which not only accelerates the convergence rate but also augments the overall convergence efficacy. The stability of the suggested control mechanism is substantiated through analytical proof, and its practicality is confirmed via simulation experiments.
This paper studies the attack detection problem for smart grids in the cyber-physical systems (CPSs) framework. In the open communication network, systems will inevitably be affected by interferences of external envir...
详细信息
ISBN:
(纸本)9798350337938
This paper studies the attack detection problem for smart grids in the cyber-physical systems (CPSs) framework. In the open communication network, systems will inevitably be affected by interferences of external environment, such as weather (naturally) and network attacks (artificially), which will cause the fluctuations of power grids. These network attacks, such as denial-of-service (DoS) attacks, will block a certain amount of signal transmission, thus reducing the performance of the load control scheme and even leading to the instability of the smart grids. First, a dynamic model is established to describe the smart grid's physical systems. Then the hypothesis of DoS attack's frequency and duration is given. A flexible, resilient controller is designed to ensure the stability of the input of the closed-loop system. An appropriate sampling mechanism is determined to achieve an effective compromise balance between system performance and communication resources. Finally, the effectiveness of the proposed method is verified by the simulation of a smart grid system.
This article proposes an adaptive neural network event triggered control scheme based on virtual parameter learning for ship automatic berthing control under false data injection (FDI) attack environment, which is sim...
详细信息
Neural networks (NNs) have been shown to learn complex control laws successfully, often with performance advantages or decreased computational cost compared to alternative methods. Neural networkcontrollers (NNCs) ar...
ISBN:
(纸本)9798350301243
Neural networks (NNs) have been shown to learn complex control laws successfully, often with performance advantages or decreased computational cost compared to alternative methods. Neural networkcontrollers (NNCs) are, however, highly sensitive to disturbances and uncertainty, meaning that it can be challenging to make satisfactory robustness guarantees for systems with these controllers. This problem is exacerbated when considering multi-agent NN-controlled systems, as existing reachability methods often scale poorly for large systems. This paper addresses the problem of finding overapproximations of forward reachable sets for discrete-time uncertain multi-agent systems with distributed NNC architectures. We first reformulate the dynamics, making the system more amenable to reachablility analysis. Next, we take advantage of the distributed architecture to split the overall reachability problem into smaller problems, significantly reducing computation time. We use quadratic constraints, along with a convex representation of uncertainty in each agent's model, to form semidefinite programs, the solutions of which give overapproximations of forward reachable sets for each agent. Finally, the methodology is tested on two realistic examples: a platoon of vehicles and a power network system.
Error introduced by Electric Power Steering (EPS) dead zones and delays in Advanced Driver Assistance systems (ADAS) significantly impacts driving safety and performance. In ADAS applications, vehicles demand heighten...
详细信息
Error introduced by Electric Power Steering (EPS) dead zones and delays in Advanced Driver Assistance systems (ADAS) significantly impacts driving safety and performance. In ADAS applications, vehicles demand heightened precision and reliability. This study addresses EPS system errors by employing a BP neural network for compensation. Initially, EPS system data pertinent to road tests was collected and subjected to correlation analysis to identify variables strongly influencing EPS system output torque. Subsequently, a neural network model of the inverse EPS system, integrating error characteristic information, was trained using BP neural networks. The model was then implemented in Simulink for validation. Comparative analysis was conducted by replaying data to contrast the model developed in this study with those derived from conventional methods. Furthermore, the model was integrated as a compensation module into the ADAS control system and tested in practical road conditions using vehicle-mounted chips. Experimental findings substantiate the effectiveness and superiority of the proposed error compensation method for engineering applications. Copyright (c) 2024 The Authors.
暂无评论