INTELLIGENT MODELING AND CONTROL OF WASHING MACHINE USING LOCALLY LINEAR NEURO‐FUZZY (LLNF) MODELING AND MODIFIED BRAIN EMOTIONAL LEARNING BASED INTELLIGENT CONTROLLER (BELBIC)

Intelligent control of home appliances has, in recent years, attracted much theoretical attention, as well as becoming a major factor for industrial and economic success and rapid market penetration. Washing Machines represent an important market. Intelligent control techniques are capable of providing useful means for both easier use and energy and water conservation. In this paper, the authors use two techniques that have successfully been used in other intelligent modeling and control applications. Firstly, the authors use a neuro‐fuzzy locally linear model tree system for data driven modeling of the machine. Secondly, the authors use a neural computing technique, based on a mathematical model of amygdala and the limbic system, for emotional control of the washing machine. The obtained results indicate the applicability of the proposed techniques in this important business sector.     

APPLICATION OF LOEVE-KARHUNEN EXPANSION TO ACOUSTIC DIAGNOSTIC PROBLEMS FOR INTERNAL COMBUSTION ENGINES

Abstract

The paper presents theoretical and applied aspects of a method concerning the detection and classification of engines' mechanical defects which can be evidenced via acoustic and vibrational emissions.

The method is based on Loève-Karhunen (L.K.) expansion of suitable pre-processed signals and provides a set of uncorrelated parameters which possess a high information content.

The method has been applied to a collection of eighteen 4-strokes internal combustion engines which included items subjectively classified as good, affected by valve knock, by connecting rod knock, or by crank rumble and the results provide automatically the original subjective classification without introducing any information concerning it.

The method also provides the means for the construction of analogical devices or implementation of suitable numerical algorithms in order to perform automatic classification of defects.     

智能控制与智能控制系统

本文首先介绍智能控制的发展和智能控制系统的结构与特点.然后,综述几种主要的智能控制系统,尤其是分级递阶智能控制系统和专家控制系统,并着重讨论它们的结构.     

MODELING AND SIMULATION FOR INTELLIGENT CONTROL OF EXPANSION VALVE IN VAPOUR COMPRESSION REFRIGERATION SYSTEM

Conventional control techniques are not able to accomplish the stable cooling in VCRS (vapour compression refrigeration system) of air conditioning system. This article describes the fuzzy modeling and simulation for intelligent control to regulate the opening area of expansion valve for better and stable refrigerant flow even in the presence of operating condition change. Fuzzy logic control of expansion valve can make a quick response to the abrupt changes of operating parameters in VCRS. The expansion valve opening trend depending upon differential pressure across it (delP) and refrigerant mass flow rate is analyzed with fuzzy modeling using ANFIS. Differential pressures in the range of 3–7 bar are sustained across the valve. Flow rates up to 0.15 kg/sec for the refrigerant R-134a have been demonstrated. The performance of the model is evaluated by comparing the predicted results with the standard mathematical model.     

智能控制与常规控制

智能控制是在常规控制理论与技术基础上的进一步发展与提高，目的是在非结构化、不确定性与控制对象有强相互作用的环境中实现过程任务（追求目标）的闭环自动控制。虽然传统人工智能方法应用于实际控制问题有很大困难，但是把对复杂环境建模的严格数学方法研究同人工智能中新兴学派思想的研究紧密结合起来，有可能导致新的智能控制体系结构的产生和发展。这种研究将会在＂自上而下＂和＂自下而上＂两个方向的交汇处取得重大突破。     

USING LEAST SQUARE SVM FOR NONLINEAR SYSTEMS MODELING AND CONTROL

Support vector machine is a learning technique based on the structural risk minimization principle, and it is also a class of regression method with good generalization ability. The paper firstly introduces the mathematical model of regression least squares support vector machine (LSSVM), and designs incremental learning algorithms by the calculation formula of block matrix, then uses LSSVM to model nonlinear system, based on which to control nonlinear systems by model predictive method. Simulation experiments indicate that the proposed method provides satisfactory performance, and it achieves superior modeling performance to the conventional method based on neural networks, moreover it achieves well control performance.     

赛事分析与预测的KDD建模

把KDD用于赛事决策支持,见之报道的还很少,本文针对一类非对垒式的,以个体成绩为主进行名次排序的体育和娱乐赛事,给出了一个该类赛事分析与预测的KDD建模方法,用于帮助分析和确定对每个参赛者的比赛成绩有影响的各种重要因素,并对比赛结果作出预测。我们的方法以轻量的、多模型的和多种技术的组合／结合为策略;兼顾到了问题的各个方面和主要特征：可以透过对几个参数的简单处理,自动、方便地对已建立的模型进行不断的修正;同时还能主动建议对模型的改进或重建,并为模型的改进或重建提供有用的帮助信息,从而能够较好地解决参赛群体多样性、多变性、影响因素的复杂性和预测的困难性等问题。     

MODELING AND CONTROL OF THE ACTIVE SUSPENSION SYSTEM USING PROPORTIONAL INTEGRAL SLIDING MODE APPROACH

The purposes of this paper are to present a new method in modeling an active suspension system for half‐car model in state space form and to develop a robust strategy in controlling the active suspension system. Proportional integral sliding mode control strategy is proposed for the system. A simulation study is performed to prove the effectiveness and robustness of the control approach and performance of the controller is compared to the linear quadratic regulator and the existing passive suspension system.     

网络控制系统的分析与建模

本文论述了网络控制系统的复杂性及当前网络控制系统建模中存在的主要缺点. 在考虑系统噪声、控制器动态及输出反馈的情况下，提出了多包传输、单包传输有数据包丢 失及多包传输有数据包丢失时网络控制系统的离散随机模型的统一的建模方法，并给出了网 络诱导时延合并定理．     

ASSESSMENT OF ELECTRICITY DEMAND IN IRAN'S INDUSTRIAL SECTOR USING DIFFERENT INTELLIGENT OPTIMIZATION TECHNIQUES

This study presents application of particle swarm optimization (PSO) and genetic algorithm (GA) methods to estimate electricity demand in Iran's industrial sectors, based on economic indicators. The economic indicators used in this study are number of customers, gross domestic product (GDP), electricity production and price. The models developed in two forms (exponential and linear). Electricity consumption in Iran's industrial sector from 1981 to 2005 is considered as the case of this study. The available data is partly used for finding the optimal, or near optimal, values of the weighting parameters (1981–1999) and partly for testing the models (2000–2005). For the best results of GA, the relative error averages were 1.13% and 1.29% for GA ? DE M _exponential and GA ? DE M _linear and for PSO were 1.03% and 1.69% for PSO ? DE M _exponential and PSO ? DEM_linear. Electricity consumption is forecasted up to year 2030.     

利用人工智能技术合成间歇过程控制步骤

本文提出了利用人工智能技术自动合成间歇过程操作控制步骤的三步策略，第一步是根据生产煤作本身的特点自动合成操作前的控制步骤，第二步是根据知识库中的知识自动合成如何执行该操作的控制步骤，第三步是合成操作后的过程控制步骤。     

EVENT-BASED INTELLIGENT CONTROL USING ENDOMORPHIC NEURAL NETWORK MODEL

In event-based control, a controller checks the responses of sensors about commands with time constraints. To do this, the event-based controller should have some information about the dynamics of the plant at discrete levels, its desired state transitions, and inputs to move the state transitions. In an existing modelling method, the information is represented by a tabular form, which is not adaptable to the variation of set positions. An artificial neural network was taken as a new modelling method to solve this problem. Experiments show that this neural network model works well in the dynamic variation of set positions. This endomorphic neural network modelling helps us to construct a more autonomous event-based controller.     

集气管压力的智能控制设计与实现

本文针地焦炉集气管压力系统具有强耦合、强干扰、典型非线性的特点,提出一种混合智能控制方法,将经典ＰＩＤ控制、前馈控制、专家控制相结合,把三种方法的简便性、可靠性、抗扰动快速性、灵活性融为一体,发挥各自的长处,并介绍了控制器的设计方法,系统实现与工业运行结果,实际运行结果了该方法的有效性     

飞机操纵系统建模及降阶仿真研究

通过对某型号飞机三轴（纵向、横向、侧向）操纵系统（机构操纵系统、增稳系统、自动加码仪系统）组成、结构及功能分析,建立了完整的数学模型。将系统分布参数分段集中化处理,在Ｍａｔｌａｂ环境下以模块化方式进行系统仿真得到了与实际系统静动态响应相吻合的仿真模型。由于飞机操纵系统模型的高阶非线性,采用“最小二乘参数拟合法”进行等效降阶处理,得到低阶带延迟环节的简化模型。这种以时域响应进行优化、频域响应进行验证     

智能车辆横向控制研究

本文分析了智能车辆横向控制特性，说明了目前一些研究中的不足，并探讨了 模糊控制方法．仿真结果表明，该算法对纵向速度、轮胎侧偏刚度以及载荷等明显影响车辆 横向运动特性的三个关键因素具有良好的适应性能．     

室外智能移动机器人的发展及其关键技术研究

室外智能移动机器人有着广泛的应用前景,是机器人研究中的热点之一．本文分析 了在室外移动机器人发展中有着代表意义的几个典型系统,进而论述了室外移动机器人研究 中的若干关键技术的研究现状及发展水平．这些关键技术包括移动机器人的控制体系结构、 机器人视觉信息的实时处理技术、车体的定位系统、多传感器信息的集成与融合技术以及路 径规划技术与车体控制技术等．     

复杂控制系统智能化建模方法及其应用

本文针对自动控制系统中普遍存在的复杂性和不确定性,为弥补传统的基于微分方程、传递函数、状态方程的建模方法的不足,将人工智能思想引入自动控制系统的建模之中,提出了基于谓词形式的自动控制系统智能语言描述方法,采用这种方法,描述自动控制系统简单方便,不仅可以描述常规的控制方法,而且可以描述专家控制、模糊控制和基于神经网络的控制等各种智能控制方法,为分析复杂系统、研究智能控制系统提供了方便。     

复杂系统的定性建模和定性控制综述

综述了复杂系统的定性建模和定性控制．首先阐述了定性建模的理论背景,讨论了 主要的定性建模研究方法及定性模型特性;接着介绍了定性控制的研究进展,对定性控制方 法进行了分类研究,探讨了定性控制器的设计及定性控制系统性能;最后就复杂系统的定性 建模和定性控制研究发展进行了评述．     

基于DNN的WSN智慧大棚可视化与控制系统研究

传统的温室大棚监测与控制系统一般采用布线方式,存在难度大、成本高等问题,已不能满足农业发展的需求。针对上述问题,研发一种基于DNN的WSN智慧大棚可视化与控制系统。在大棚内部署LoRa传感器网络采集环境信息。为直观地表达大棚内环境因子分布情况,采用Kriging方法构建环境因子分布图,并利用DNN神经网络建立专家知识库,能够自主科学地决策。通过反馈控制系统调节大棚内环境,使农作物具有最佳的生长环境。实验结果表明,该系统能够较好地展现环境因子分布情况且能够科学地调节大棚环境。