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。     

逻辑—对象知识模型LOKM

知识模型是知识信息处理系统的重要基础,是建立知识系统的主导思想,提供知识表示和操作的形式构架。在近几年研究的基础上,我们提出了逻辑-对象知识模型LOKM。本文主要讨论该模型的知识结构和推理策略。     

基于深知识的YGR-1型自动机器人系统

提出了一种自动机器人系统的结构,在该系统对处理世界进行了模型化,建立了对象模型深知识库,在控制机器人动作序列的生成中,模仿了人的思维方式,提出了一种将基于模型的推理和并行推理技术应用于机器人任务规划与控制的方法,并设计了推理程序。     

基于电流信号估计抓握力的假肢手抓握控制

为避免假肢手需外置力传感器进行抓握力控制的不足,提出了一种通过电流信号估计抓握力的假肢手抓握力控制方法。根据假肢手模型、接触力模型和直流(DC)电机模型建立基于电流信号的假肢手抓握力估计模型,将抓握力估计模型与比例—积分—微分(PID)控制器结合,在无需外置力传感器的情况下对假肢手进行抓握力控制。抓握控制仿真和实验表明:所提出的假肢手抓握力估计方法和控制方法有效。     

面向对象知识库的设计

面向对象技术的成熟及其在知识库系统中的应用，赋予了知识库一些新的概念。我们就此进行了较为深入的研究，并对知识表达、推理等作了一些探讨，采用基于面向对象技术的原型－代理机制定义和设计了知识对象，实现了知识共享，并通过对象间的消息传递形成多个推理机场境，从而进行知识的推理。本课题初步实现了一个具有一定推理辅助决策能力的原型知识库系统。     

航空瞄准具故障诊断专家系统中知识的处理方法

针对航空瞄准具故障诊断专家系统中知识的获取、表达和推理方法等问题进行研究;首先根据瞄准具的结构特点建立了层次诊断模型,并根据模型在系统中采用了故障树分析法;然后着重讨论了系统中知识的表达、推理和模糊推理等问题的处理方法;通过在系统中建立层次结构的综合数据库及采用产生式规则,有利于诊断知识的获取和表达;采用全局择优搜索法、双向推理和模糊推理,大大提高了推理的效率;该方法的应用为瞄准具故障诊断专家系统的开发和完善提供了有力的技术支持.     

基于知识支持的建筑施工质量控制系统研究

将知识管理的理念应用到施工质量控制中,加速施工质量控制中知识的循环过程,提高工程质量预测控制和事故诊断能力。通过湖北省建筑工程质量控制研究实践,开发了集建筑质量控制知识管理和决策支持功能于一体的施工质量控制和事故处理系统(CQIS),系统将正向规则推理和基于案例的推理(CBR)相结合,通过RBR接口调用RBR系统,提高案例推理质量诊断的能力,实现基于知识的综合推理功能。该系统已经获得科技成果鉴定和湖北省科技推广成果。     

基于浅层知识和深层知识推理的故障诊断专家系统工具

以专家系统和诊断问题求解为基础，建立了基于浅层知识和深层知识推理相结合的故障诊断专家系统工具。文中论述了工具的结构、知识表示、参数设计、推理机制、黑板控制、学习机制和其它支持环境。     

基于Visual Basic 6.0的故障智能诊断系统设计方法的研究

采用面向对象方法和 ＶＢ６．０程序设计语言,开发了一个故障智能诊断平台系统,该系统可针对不同对象建立诊断任务和环境。文章首先介绍了该系统的结构和各模块的功能,然后阐述了系统知识库建立的方法和推理机制。系统采用模糊推理与规则推理相结合的方法,具有较高的准确性。最后给出了一个系统的诊断实例。     

染色体识别专案系统的实现

本文提出了一个应用于染色体自动识别的基于模式识别的专家系统结构。系统由静态数据库、推理控制、染色体特征抽取、解释功能和知识获取等五个主要部分组成。知识表达采用框架知识表示方法描述染色体的层次结构特征。推理机制采用混合双向推理,并提出了适合于本系统的CF模型。该系统在IBM-PC机上实现,选用Turbo-PROLOG和Turbo-C共同作为系统的实现语言。在专家系统骨架完成以后,把人类染色体作为实例,建立起一个人类染色体识别专家系统。     

基于虚拟现实技术的多功能肌电假肢控制系统开发平台

利用虚拟现实技术开发的多功能假肢控制系统开发平台,可以研究肌电解码控制多功能假肢的实时操控性能,便于对影响多功能肌电假肢临床控制性能的动态因素及如何提高和改善多功能肌电假肢控制性能进行详细的研究.另外,肌电假肢的使用存在训练过程漫长、使用者精神负担大等问题,利用虚拟手代替真实肌电手进行训练,可以营造一种轻松训练环境;本系统利用SolidWorks绘制出三维手臂,再用虚拟现实三维建模方法和建模语言(VRML)节点语法编辑出完整的虚拟手臂场景,利用MATLAB中的simulink工具搭建虚拟手控制平台,实现虚拟世界和外界的交互;该系统可以通过从残疾人残余肌肉采集的肌电信号进行解码、时域特征提取、动作类型识别等操作,最终实现用肌电信号控制虚拟手臂.     

一种基于多传感器的步态相位实时检测系统

对人体步态相位进行准确实时的判断是智能假肢等康复机器人控制的基础,提出并建立了一种实时状态相位检测系统.该系统包含了4只压力传感器和2只姿态传感器,能够准确地区分出平地行走时足跟着地、足放平、足跟离地、足尖离地、摆动弯曲以及摆动伸展等五种状态相位,实验表明:该系统能够适应不同测试者的不同步幅和步速,并能够应用在假肢的实时控制中.     

The role of quantitative information about slip and grip force in prosthetic grasp stability

Prosthetic hands introduce an artificial sensorimotor interface between the prosthesis wearer and the environment that is prone to perturbations. We analyze theoretically and evaluate psychophysically the performance in stable grip control in conditions of physical grasps perturbation, such as object slip. Simulation results suggest that user-centered stable grasp control depends on two primal user parameters: reaction time to slip and grip force intensity. Experiments with human users indicate that a user’s response time can be controlled by relaying information about the speed of the slipping object, while minimal grip force intensity can be adjusted with information about grip force at the onset of the slip. Based on our theoretical and experimental findings, we propose a stable grasp control method for prosthetic hands.     

基于触觉和肌电信号的假手模糊控制方法研究

提出了一种带触觉反馈的肌电假手模糊控制方法．该方法在有效识别肌电信号(MES)的基础上,实现了基于触觉与肌电信号的假手仿生控制．为了消除肌电信号的个体差异,使其能可靠应用于非特定人场合,应用互功率谱比值法对肌电信号进行处理,并分析互功率谱的各项参数和对应肢体动作变化之间的关系,消除了肌电信号实际测量中不可测噪声的干扰．采用特别设计的模糊控制器控制假手动作的步进量,实现了肌电假手对多种不同物体的稳定抓取．实验表明这种组合方法不仅可以获得较高的动作模式识别率,而且能有效地降低被抓取物体的损坏．     

基于BMI模型的三关节假肢运动的优化控制

生物神经系统一直以来被作为机器人控制器的研究灵感之一,人们试图借用以生物为启发的控制模型来控制外部设备,使得其能达到类似生物般的运动效果.鉴于此,以一种模拟大脑皮层神经元放电活动为基础的闭环脑-机接口(BMI)模型为控制器,控制简化后的三关节人工假肢完成目标位置的抓取动作,并在给定目标距离下,建立三关节假肢的简化模型,由此提出时间与动能的损失函数以描述假肢运动过程产生的损耗.最后利用一种贝叶斯迭代算法求取假肢的最佳运动方式,使其在完成目标抓取动作时损失函数值最小,进而完成对假肢运动控制的优化并取得较好的控制效果.     

Human Model Reference Adaptive Control of a Prosthetic Hand

A human model reference adaptive controller (HMRAC) is developed for a prosthetic hand. The model reference for the adaptive controller is formed from grasp experiments with human test subjects. This HMRAC is incorporated within a hybrid force-position control law; electromyogram (EMG) signals from amputee and nonamputee test subjects are used to control the force or position of the prosthetic hand. The HMRAC is compared to a sliding mode controller (SMC) with high and low control gains during bench top experiments with step and EMG inputs while grasping high and low stiffness objects. Results from the bench top experiments show that the SMC with a high control gain produced the least amount of tracking error with the EMG input at the expense of a highly oscillatory system response while grasping the high stiffness object. The HMRAC produced less tracking error with the step inputs in all cases and less tracking error with the EMG input in comparison to the SMC with a low control gain. The HMRAC also produced less percent overshoot (OS) with the step inputs on average in comparison to the SMC in all cases. Experiments were also performed by a transradial amputee with the SMC and the HMRAC. Both controllers were compared to the amputee’s current prosthesis for daily use. Results from the experiments performed by the amputee with the HMRAC and the SMC were similar to the bench top experiments: the high gain SMC had the least tracking error on average at the expense of a highly oscillatory system response with high object stiffness. The HMRAC was not oscillatory and had the next lowest amount of tracking error than all other prosthesis control options. The HMRAC had slightly more error than the amputee had while using his natural left hand. Similar results were obtained from seven nonamputees who also participated in this study.     

Improvement of a neural network-based motion generator with bimanual coordination for upper limb prosthesis

We propose to redesign a neural network used as a motion generator with bimanual coordination for upper limb prosthesis in order to improve its learning capability. We assumed that the wearer of the prosthesis was a unilateral amputee. In our previous work, we proposed a prosthesis control system using a neural network that learned bimanual coordination in order to implement smooth motion with both hands. However, the previously proposed system has the problem that a neural network cannot generate the desired motion of the prosthesis in special cases. The reason is that the motion generator calculates the desired posture of the prosthesis from the current posture of the healthy arm only, regardless of the current posture of the prosthesis. We propose to use the current posture of both the healthy arm and the prosthesis as neural network inputs in order to solve this problem. In this article, we show that a single neural network whose input was the current posture of both arms could learn the relationships of the coordinated motions of holding boxes of different sizes, and the newly proposed system can calculate the desired motion of the prosthesis in special cases through computer simulations.     

具有感觉反馈的仿生假手人机交互研究

仿生假手是一个典型的生机电一体化系统.针对现有假手缺乏感觉反馈的问题,研究了具有双向信息传输能力的生机电一体化假手人机交互系统.采用压力传感器阵列检测肌肉压力分布信号,通过压力分布图的构建,基于主成分分析的特征提取和基于KNN分类器的特征识别方法实现了人手多运动模式的解码.基于假手力传感器,采用电刺激方式实现了假肢接触力向人体的感觉反馈.实验表明,基于肌肉压力分布信号的手部多运动模式识别方法具有较高的正确率,采用具有感觉反馈的交互控制系统可提高假手的抓取能力.     

免疫最优PID控制器设计与应用

以基于欧氏距离和精英交叉的人工免疫算法(DKBAIA)为基础,提出了一种新的最优PID控制器的设计方法。这种方法的核心是以ITAE性能准则为目标函数,采用DKBAIA去调整和优化PID控制器参数,以获得最优的目标函数值,进而获得最优的PID控制器。所设计的这种控制器称为DKBAIA—PID控制器。将该控制器用于控制智能仿生人工腿的执行电机中,并进行计算机仿真实验,结果表明:这种基于免疫算法的最优PID控制器具有良好的动态和稳态性能。     

Construction of a robot control system which understands a voice and pointing actions

This research was aimed at making a robot that can go and get an object designated by the user. We produced a robot control system that uses pointing and voice control. This control system is composed of two systems. One system is the object instruction system that uses pointing, and the other is the object instruction system that uses voice. The approximate position of a designated object is recognized by the object instruction system that uses pointing, and information about the object and instructions about the operation are conveyed by the object instruction system that uses voice. This time, the object instruction system that uses pointing has been designed and verified as the first step. A calculation resource to calculate the approximate position of the designated object is obtained when the user points directly at the object. A robot can be moved around a designated object by using this system. The object instruction system that uses voice will be constructed in future work.