智能装配机器人机械零件知识库的自动建立

为了实现智能装配机器人能够模拟人装配机械零件,系统应包含有关装配所必需的知识.利用这些知识,机器人自动编制装配工艺规程.并自动安排机器人的一系列控制命令.机械零件知识库是基于知识的智能装配机器人规划系统中不可缺少的知识.本文介绍了由机器人的视觉系统摄入机械零件图纸后,如何由摄入的二值化图形自动建立机械零件知识库.     

PKS体系下基于知识图谱的政务问答机器人研究

提出了一种基于国产PKS环境上政务知识库问答机器人。该系统基于多源异构数据，利用深度学习模型，以流水线工作方式，由Schema设计、知识抽取、知识融合、知识存储、知识更新5部分组成，自动完成知识库建立，同时自动对用户问题进行分类，意图识别，利用知识图谱检索、分析计算技术形成答案提供给用户。该机器人系统能够大大提高政务工作人员的工作效率。     

加工仿真系统中弯管类零件加工工艺信息的自动提取

在加工仿真系统中 ,加工工艺信息的自动生成对于提高仿真系统的自动化、实用化水平 ,减少工艺人员的工作负荷至关重要。该文针对弯管零件加工仿真系统 ,提出了加工工艺信息自动提取方法。该方法根据弯管零件的数字化模型 ,自动判断曲面的类型 ,生成各曲面间的拓扑关系 ,提取每个曲面的几何参数及相关曲面的位置关系信息 ,并将这些信息转为工艺参数 ,输入工艺知识库 ,再根据相应的工艺知识 ,生成加工工艺信息。     

基于神经网络的足球机器人决策知识库的设计

本文主要提出一种基于神经网络的足球机器人决策知识库的构建方案,阐述了所设计的决策知识库的知识构成和相应的知识表达方法。根据该知识库的知识构成特点,将神经网络运用于知识库的知识表达与获取之中,利用神经网络的自组织和学习能力,提高知识库的推理能力和在线决策能力。最后利用VC6.0,以RoboCup中型组比赛为例进行仿真论证。     

基于对象模型的自适应模糊专家控制系统

文中介绍了一个基于对象模型的自适应模糊专家控制系统。在该系统里,能动地机器人的行走装置进行模型化,建立了对象的模糊知识库,并根据自适应模糊控制的目标设计了推理机。系统无需铁数学模型,能根据输入、输出变量自动个性控制规则,达到优化控制钵文还介绍了对象模型的模糊知识表示方法和模糊知识库的结构以及对象模型的模糊控制推理。     

码垛机器人运动学分析及仿真研究

针对当前码垛机器人实际运动规划难度较大的问题,以某真实生产线上六自由度码垛机器人为研究对象,采用D-H法建立机械臂数学模型,对机械臂的正运动学、逆运动学进行分析,确定码垛机器人的工作空间。使用Robot Studio软件对末端机械爪、托盘、物料、传送链等进行建模,完成虚拟场景空间布局,通过编程实现码垛机器人的运动仿真。经综合调试,系统工作稳定、可靠,对现阶段码垛机器人的设计与仿真有一定借鉴意义。     

基于势函数的多机器人系统的编队控制

提出了一种基于势函数的、能够有效地对多机器人系统的编队队形进行稳定性分析和分布控制的方法．文章通过选择适当的、与目标和结构相关的势函数,利用图论知识和李亚普诺夫稳定理论,设计了一种新颖的能够稳定机器人编队队形并有效跟踪目标的分布控制律,并给出了多机器人系统编队队形稳定及控制问题有解的充分条件．算例仿真说明了这种控制方法的有效性．     

煤矿掘进机器人虚拟仿真与远程控制系统

针对现有掘进机视频监控和遥测遥控等监控方式存在图像不清晰、无法真实反映掘进机位姿和工况状态等问题,提出了一种煤矿掘进机器人虚拟仿真与远程控制系统,介绍了系统方案设计,对掘进机器人改进设计、虚拟仿真远程监控平台、掘进机器人控制模型等关键技术进行了研究。该系统利用虚拟现实技术有机整合井下操作人员、掘进机器人和井下环境信息,以掘进机器人自动掘进和远程人工干预为目的,实现了掘进过程的运动控制和巷道成型掘进控制功能。实验结果验证了该系统的有效性和良好的控制性能。     

基于云控制的业务服务机器人系统设计

文中提出一种基于云控制的业务引导机器人系统的设计方案。系统的硬件部分由摄像头和光电传感器等模块组成。在机器人系统中采用深度强化学习,实现了对未知环境的预测,提高机器人对环境的适应能力。仿真结果表明:机器人可实现路线识别和自动导航的功能,能较好适应未知环境、及时完成业务的引导工作;该系统设计合理,操作简单,具有一定的市场价值。     

基于ROS的协作机器人控制系统

为了实现协作机器人的控制,对协作机器人进行了控制系统研究,在保证系统鲁棒性和实时性的前提下,提出了在PC机上,构建基于Ubuntu系统下结合ROS,利用CAN通讯的方式,搭建协作机器人的控制系统.最后通过仿真实验和实体机器人控制实验,验证协作机器人控制系统应用效果.实验结果表明,该协作机器人控制系统具备控制协作机器人进行路径规划的基本工作能力,能够很好的建立上下位机的通讯,进行协作机器人控制.同时本控制系统具有模块化、可移植性高、框架清晰、低延时等特点.     

Simultaneous control of vehicle routing and inventory for dynamic inbound supply chain

This paper investigates inbound logistics for an OEM (Original Equipment Manufacturing) manufacturer, who aims at short production time and JIT policy. In such a case, it can be argued that the inbound vehicle routing schedule should be combined with incoming parts inventory control. In this paper, we propose a simultaneous control method of combining vehicle scheduling and inventory control for such dynamic inbound logistics. For the transportation control, a vehicle routing system, in which delivery jobs are made with shipments of one supplier, is proposed to generate a vehicle routes plan by considering production start time, travel time, waiting time, and loading/unloading time. To evaluate the performance of the generated vehicle routing plan, a goal model is also developed by considering vehicle operating cost, stock level exceeding penalty, and transportation efficiency. A generated vehicle routing plan can be rejected when the stock level is over the capacity and an appropriate number of vehicles for its manufacturing environment can be determined. Using real data from an LCD firm, a simulation study is conducted. The simulation results indicate that the simultaneous control approach requires fewer vehicles than the existing system and shows better efficiency of transportation. This method can also be used to determine the appropriate incoming part inventory level or the number of vehicles required in dynamic inbound logistics.     

空间站交会对接的一种智能控制方法与仿真

本文研究了空间站交会对接阶段的仿人智能控制问题，设计了相应的特征模型和控制逻辑，建立了系统的知识库、数据库、规则库和推理机等。最后通过对两个飞行器的空间交会对接过程的数字仿真，验证了所设计的智能控制方案的有效性。     

基于模糊控制技术的热轧带钢卷取温度控制

针对宝钢热轧厂层流冷却控制系统提出了一种温差模糊控制策略 ,以克服带钢头部和尾部温差精度低的缺点。通过对实际数据的分析 ,获得了完整的模糊控制规则集。模拟轧制表明该新型智能控制系统是成功的。     

快速批仿真及其在控制系统设计中的应用

提出用快速成批仿真的办法辅助设计控制系统,并介绍了作者编制的软件.快速成批仿 真也可用来建立控制系统智能设计所需的知识库及检验系统的鲁棒性.文中给出了两个应用 实例.     

Flexible control in expert systems for construction tasks

In most expert systems for constructional tasks, the knowledge base consists of a set of facts or object definitions and a set of rules. These rules contain knowledge about correct or ideal solutions as well as knowledge on how to control the construction process. In this paper, we present an approach that avoids this type of rules and thus the disadvantages caused by them.We propose a static knowledge base consisting of a set of object definitions interconnected by is-a and part-of links. This conceptual hierarchy declaratively defines a taxonomy of domain objects and the aggregation of components to composite objects. Thus, the conceptual hierarchy describes the set of all admissible solutions to a constructional problem. Interdependencies between objects are represented by constraints. A solution is a syntactically complete and correct instantiation of the conceptual hierarchy.No control knowledge is included in the conceptual hierarchy. Instead, the control mechanism will use the conceptual hierarchy as a guideline. Thus it is possible to determine in which respects a current partial solution is incomplete simply by syntactical comparison with the conceptual hierarchy. The control architecture proposed here has the following characteristics: separation of control and object knowledge, declarative representation of control knowledge, and explicit control decisions in the problem solving process. Thus, a flexible control mechanism can be realized that supports interactive construction, integration of case-based approaches and simulation methods.This control method is part of an expert system kernel for planning and configuration tasks in technical domains. This kernel has been developed at the University of Hamburg and is currently applied to several domains.     

Data-driven optimal control of switched linear autonomous systems

In this paper, a novel data-driven optimal control approach of switching times is proposed for unknown continuous-time switched linear autonomous systems with a finite-horizon cost function and a prescribed switching sequence. No a priori knowledge on the system dynamics is required in this approach. First, some formulas based on the Taylor expansion are deduced to estimate the derivatives of a cost function with respect to the switching times using system state data. Then, a data-driven optimal control approach based on the gradient decent algorithm is designed, taking advantage of the derivatives to approximate the optimal switching times. Moreover, the estimation errors are analysed and proven to be bounded. Finally, simulation examples are illustrated to validate the effectiveness of the approach.     

井下调度运输的自动调度策略研究

为了提高煤矿井下机车调度效率和实现井下调度系统自动化,基于Petri网理论知识结合实际井下矿场路况建立机车调度Petri网模型,然后对Petri网模型添加限制库所和变迁使其调度过程无死锁,并通过理论证明了该调度模型是无死锁和冲突的,可以指导机车井下运输调度.然后在机车调度规则下针对不同的井下机车调度相关参数,提出了3种...     

HAVC系统变电站多目标优化控制策略

变电站电压无功控制是电网混成自动电压控制(hybrid automatic voltage control,HAVC)系统的重要组成部分,其控制措施一般包括变电站有载调压变压器(OLTC)的调节和站内电容电抗器的投切等.变电站电压无功控制器设计是一个典型的多目标优化问题.即在调控过程中,既要控制无功及电压尽量接近设定值,又必须使OLTC的调节次数和电容电抗器的投切次数尽量少.因此,本文首先建立了HAVC系统变电站电压无功控制的多目标优化模型,然后求解该多目标优化问题得到变电站电压无功优化控制策略.对东北电网沙岭变电站的仿真分析证明了所提出的控制策略的有效性和正确性.     

Manufacturing system application of a knowledge based simulation

The flexibility in a modern manufacturing facility introduces complexity to the decision making. The requirement for a real time control mechanism results in a need for an on-line simulation system that can simulate the complicated scheduling, routing and similar decisions required by the system.

This paper describes a knowledge-based simulation and control system written in PROLOG. This system is composed of four parts: a static data base, a dynamic database, a modeling knowledge part, and a simulation driver. The simulator contains the actual control mechanism of the physical system and can be removed from the system in order to simulate it.

The manufacturing system under investigation is a combination of flexible manufacturing cells that feed an automated assembly station. The knowledge-based simulation helps to develp and understand control mechanisms for that system, which can later be implemented in the physical system as the controller.     

飞机座舱压力专家模糊预控方法仿真研究

针对新型战机高空高速俯冲及俯冲转平飞情况下带来的座舱压力控制难题,提出一种飞机座舱压力专家模糊PID预控方法。在飞机高速俯冲时,基于压力调节系统时间延迟及飞机高度变化率改进常规模糊PID控制策略并提高座舱压力调整速度;在飞机状态转换时,利用专家控制器根据知识库及状态转换时间预测调整模糊PID控制策略,并引入重置机制以改善调整性能。经过知识库的动态学习,得出飞机状态转换时,采用模糊PID控制、模糊预控、重置PID控制参数的专家控制策略具有最佳的控制效果的结论。通过仿真实验验证了该方法的有效性。