Multi-agent reinforcement learning for online scheduling in smart factories

Rapid advances in sensing and communication technologies connect isolated manufacturing units, which generates large amounts of data. The new trend of mass customization brings a higher level of disturbances and uncertainties to production planning. Traditional manufacturing systems analyze data and schedule orders in a centralized architecture, which is inefficient and unreliable for the overdependence on central controllers and limited communication channels. Internet of things (IoT) and cloud technologies make it possible to build a distributed manufacturing architecture such as the multi-agent system (MAS). Recently, artificial intelligence (AI) methods are used to solve scheduling problems in the manufacturing setting. However, it is difficult for scheduling algorithms to process high-dimensional data in a distributed system with heterogeneous manufacturing units. Therefore, this paper presents new cyber-physical integration in smart factories for online scheduling of low-volume-high-mix orders. First, manufacturing units are interconnected with each other through the cyber-physical system (CPS) by IoT technologies. Attributes of machining operations are stored and transmitted by radio frequency identification (RFID) tags. Second, we propose an AI scheduler with novel neural networks for each unit (e.g., warehouse, machine) to schedule dynamic operations with real-time sensor data. Each AI scheduler can collaborate with other schedulers by learning from their scheduling experiences. Third, we design new reward functions to improve the decision-making abilities of multiple AI schedulers based on reinforcement learning (RL). The proposed methodology is evaluated and validated in a smart factory by real-world case studies. Experimental results show that the new architecture for smart factories not only improves the learning and scheduling efficiency of multiple AI schedulers but also effectively deals with unexpected events such as rush orders and machine failures.     

基于分布式智能代理的入侵检测方法研究

在分析和研究通用入侵检测框架理论和传统入侵检测系统实现策略的基础上，提出融合了滥用检测和异常检测两种方法的检测模型——基于分布式智能代理的网络入侵检测模型，并对检测引擎和检测算法进行了改进，使之具有更高的准确性和对潜在的入侵行为的识别和预测等智能化能力。     

基于多智能体通讯机制的多机器人编队系统

源于分布式人工智能的多智能体系统,以其突出的灵活性和适用性,被应用于多机器人协调系统领域。论文从多智能体理论出发,研究在真实世界里利用多协议全双工的通讯机制如何来实现多智能体机器人系统的技术和方法,并通过编队试验对系统性能进行验证。结果表明系统的构建是稳定可行的。     

Distributed Computation Multi-agent System

This article addresses a formal model of a distributed computation multi-agent system. This model has evolved from the experimental research on using multi-agent systems as a ground for developing fuzzy cognitive maps. The main paper contribution is a distributed computation multi-agent system definition and mathematical formalization based on automata theory. This mathematical formalization is tested by developing distributed computation multi-agent systems for fuzzy cognitive maps and artificial neural networks – two typical distributed computation systems. Fuzzy cognitive maps are distributed computation systems used for qualitative modeling and behavior simulation, while artificial neural networks are used for modeling and simulating complex systems by creating a non-linear statistical data model. An artificial neural network encapsulates in its structure data patterns that are hidden in the data used to create the network. Both of these systems are well suited for formal model testing. We have used evolutionary incremental development as an agent design method which has shown to be a good approach to develop multi-agent systems according to the formal model of a distributed computation multi-agent system.     

基于多Agent的网上教学系统模型的研究

随着人工智能技术的不断发展和完善,人工智能领域的理论(特别是Agent技术)不断地被应用到网上教学系统(NTS,Network Teaching System)中,从而给NTS的研究与应用提供了新的发展空间。文中设计了一个基于多Agent的网上教学系统模型,详细描述了本NTS结构的三层:应用层、集成层、数据层,及多Agent的通信机制。     

相继增压柴油机试验台测控系统设计

发动机台架试验是发动机性能测试的主要手段,采用计算机控制的自动测试与控制系统是其发展的必然趋势。以NI多功能数据采集(DAQ)卡硬件为基础,自主设计了发动机各种测量和控制信号的调理和控制电路;以LabVIEW为上位机软件开发环境,开发了相继增压柴油机试验台测控软件,实现了对柴油机工况及相继增压系统的控制以及对各参数的采集、显示、存储、回放、报警等功能。通过对该系统的测试,表明系统功能完善、测试和控制精度较高、运行稳定可靠,达到了预期目标。     

基于多Agent的复合模型求解自适应QoS机制

在基于网络的分布式系统应用基础上，分析了大型复杂问题复合模型协作求解的过程特征描述，提出基于多Agent 的领域问题协作求解的主动控制策略，探讨了用户交互Agent、系统主控Agent、协作Agent以及模型Agent和数据Agent等复合模型协作求解的4种Agent类型。应用多Agent层次结构，提出一种复合模型协作求解的自适应QoS体系结构，通过实现复合模型协作求解的主动调度规划算法对其进行了验证，支持分布式网络环境下实现模型资源和数据资源的共享，以提高协同计算环境分布式问题协作求解的运行效率和服务质量。     

Design of Diesel Engine Mathematical Model Oriented to Speed Control

We provide the synthesis procedure for a mathematical model of the 20ChN26.5/31 diesel engine treated as a part of 20EDG500 diesel-electric set (power 6.3 MW). The model is designed for synthesis of engine speed control and simulation of closed-loop control systems in generator sets. The model structure is based on the fundamental laws of physics, while its parameters and static functions are obtained using least squares approach and the data taken during experimental testing of the set. The results of model verification are presented, and the model outputs are compared with the experimental data. Simulation of the control system closed by proportional-integral-differential law is presented as an example of the model application.     

船舶柴油机故障诊断仿真系统研究

该文阐述了船舶柴油机故障诊断仿真系统的模型、结构与功能,着重介绍了基于RBF神经网络故障诊断方法。本系统具有结构简单、功能齐全等优点,对开发实船柴油机故障诊断的辅助分析系统和培训轮机员熟悉处理故障有实际意义。     

Impulsive observer-based consensus control for multi-agent systems with time delay

The paper deals with the distributed consensus problem of a class of general linear multi-agent systems with time delay. Assuming that the state of the multi-agent system cannot be measured and the output of the multi-agent system is measured discontinuously, a novel impulsive observer is constructed. Based on the impulsive observer, a distributed consensus protocol is proposed for the multi-agent system with a directed communication topology. In view of the hybrid characteristic of the multi-agent system with the impulsive observer, a novel type of piecewise Lyapunov functional which can overcome the jump phenomena at impulsive times is introduced. Based on this, some sufficient conditions in terms of linear matrix inequalities are presented such that the consensus of the multi-agent system can be achieved with an exponential convergence rate. A numerical example under two cases is given to show the effectiveness of the theoretical results.     

煤矿用防爆柴油机冷却风扇液压驱动系统研究

防爆柴油机是煤炭开采设备使用的主要动力源。当前防爆柴油机冷却系统风扇主要采用传统曲轴定转动比驱动,无法完全适应煤矿井下复杂的工作条件,造成风扇功耗大,冷却效果差,空间布置受限等问题。本文研究了防爆柴油机冷却系统结构,提出了采用液压驱动方式,分别对冷却系统中的不同组成进行独立控制的解决方案,从而改善了系统过热、过冷情况。将风扇与防爆柴油机分开布置,使得系统设计更加灵活,可以适应更多的应用场合。     

汽车企业智能化动态联盟的构建

针对目前国内外汽车工业的发展趋势,根据人工智能的思想,提出了构建汽车企业智能化动态联盟的框架,并借助多智能体系统开发平台JADE来实现系统框架的运行。这一概念的提出,不仅符合汽车企业现代化管理的发展方向,还对多智能体技术的应用推广起到一定的促进作用。     

船舶电站柴油机双脉冲H∞调速器的研究

船舶电力系统频率的稳定性主要取决于船舶电站柴油机调速系统的转速响应特性.为了抑制负荷的扰动, 提高柴油机双脉冲调速器的动态精度, 本文将H_∞控制理论应用于柴油机调速系统的设计,将系统的性能要求转化为标准H_∞控制问题.建立了采用双脉冲${\rm H}_\infty$调速器的柴油机调速系统的数学模型,针对外部干扰和模型的不确定性, 双脉冲H_∞调速器的设计可以归结为混合 灵敏度问题.计算机仿真实验结果表明, 本文设计的双脉冲H_∞调速器能在充分考虑系统模型不确定性的情况下,有效提高系统的动态 精度和抑制扰动的能力,改善船舶电力系统频率的稳定性.     

船舶电站柴油机双脉冲H∞调速器的研究

船舶电力系统频率的稳定性主要取决于船舶电站柴油机调速系统的转速响应特性．为了抑制负荷的扰动,提高柴油机双脉冲调速器的动态精度,本文将H_∞控制理论应用于柴油机调速系统的设计,将系统的性能要求转化为标准H_∞控制问题．建立了采用双脉冲H_∞调速器的柴油机调速系统的数学模型,针对外部干扰和模型的不确定性,双脉冲H_∞调速器的设计可以归结为混合灵敏度问题．计算机仿真实验结果表明,本文设计的双脉冲H_∞调速器能在充分考虑系统模型不确定性的情况下,有效提高系统的动态精度和抑制扰动的能力,改善船舶电力系统频率的稳定性．     

Improving the security level of the FUSION@ multi-agent architecture

The use of architectures based on services and multi-agent systems has become an increasingly important part of the solution set used for the development of distributed systems. Nevertheless, these models pose a variety of problems with regards to security. This article presents the Adaptive Intrusion Detection Multi-agent System (AIDeMaS), a mechanism that has been designed to detect and block malicious SOAP messages within distributed systems built by service based architectures. AIDeMaS has been implemented as part of FUSION@, a multi-agent architecture that facilitates the integration of distributed services and applications to optimize the construction of highly-dynamic multi-agent systems. One of the main features of AIDeMaS is that is employs case-based reasoning mechanisms, which provide it with great learning and adaptation capabilities that can be used for classifying SOAP messages. This research presents a case study that uses the ALZ-MAS system, a multi-agent system built around FUSION@, in order to confirm the effectiveness of AIDeMaS. The preliminary results are presented in this paper.     

基于多代理技术可自检的分布式入侵检测系统模型

通过对现有多代理技术的分布式入侵检测系统的研究,提出了一种基于多代理技术可自检的分布式入侵检测系统模型,并且对该模型的结构,组成和代理的处理流程进行了描述,该模型是一个开放的系统模型,具有很好的可扩展性,易于加入新的入侵检测代理及相应的自检,也易于增加新的入侵检测模式,代理之间的协同采用代理守护进程来实现。     

场景图谱驱动目标搜索的多智能体强化学习

针对强化学习在视觉语义导航任务中准确率低,导航效率不高,容错率太差,且部分只适用于单智能体等问题,提出一种基于场景先验的多智能体目标搜索算法。该算法利用强化学习,将单智能体系统拓展到多智能体系统上将场景图谱作为先验知识辅助智能体团队进行视觉探索,利用集中式训练分布式探索的多智能体强化学习的方法以大幅度提升智能体团队的准确率和工作效率。通过在AI2THOR中进行训练测试,并与其他算法进行对比证明此方法无论在目标搜索的准确率还是效率上都优先于其他算法。     

内燃机车柴油机燃烧状态智能检测系统研究

内燃机车柴油机燃烧状态智能检测系统是专门应用于机车检修现场的柴油机故障检测装置,由便携式测温仪和计算机检测系统组成.红外测温枪实时检测柴油机气缸的燃烧状态,通过RS232串口与计算机进行数据通讯.计算机检测系统对红外测温仪数据进行分析、处理,自动识别、判断出柴油机的故障,自动生成报表.该系统为柴油机检修提供了先进的故障诊断方法和手段,为柴油机的保养和检修提供了可靠依据,减小了机车的检修难度,大大提高了内燃机车的检修效率.     

Infrastructure for Design, Deployment and Experimentation of Distributed Agent-based Systems: The Requirements, The Technologies, and An Example

This paper discusses infrastructure for design, development, and experimentation of multi-agent systems. Multi-agent system design requires determining (1) how domain requirements drive the use of agents and AI techniques, (2) what competencies agents need in a MAS, and (3) which techniques implement those competencies. Deployment requirements include code reuse, parallel development through formal standardized object specifications, multi-language and multi-platform support, simulation and experimentation facilities, and user interfaces to view internal module, agent, and system operations. We discuss how standard infrastructure technologies such as OMG IDL, OMG CORBA, Java, and VRML support these services. Empirical evaluation of complex software systems requires iteration through combinations of experimental parameters and recording desired data. Infrastructure software can ease the setup, running, and analysis of large-scale computational experiments. The development of the Sensible Agent Testbed and architecture over the past six years provides a concrete example. The design rationale for the Sensible Agent architecture emphasizes domain-independent requirements and rapid deployment to new application domains. The Sensible Agent Testbed is a suite of tools providing or assisting in setting up, running, visually monitoring, and chronicling empirical testing and operation of complex, distributed multi-agent systems. A thorough look at the various Sensible Agents infrastructure pieces illustrates the engineering principles essential for multi-agent infrastructure, while documenting the software for users.     

基于XML的入侵检测主体通讯机制

良好的通讯机制是基于多主体技术的分布式入侵检测系统正常运行的前提保证 ,根据入侵检测中主体间通讯的特点并结合我们所设计的基于多主体技术的分布式入侵检测系统 ADIDS的具体要求 ,设计了一种入侵检测主体之间进行入侵信息交换的通讯语言 IDACL,并在此基础上提出了一种基于 XML 的、适用于入侵检测主体间协作和信息交换的通讯机制 X- IDACM,可满足基于多主体技术的分布式入侵检测系统中各个主体间的通讯需求