汽车故障诊断专家系统的设计与实现

针对目前汽车故障的复杂多样以及无法实时诊断的情况,提出了基于规则的汽车故障诊断专家系统。该系统运用汽车故障诊断专家的知识填充知识库,运用人工智能的理论,以产生式规则作为知识的表示形式,采用基于故障树的分析方法,运用正向推理,达到对汽车基本故障诊断的目的,实现对汽车实时故障的诊断。     

磨粒识别神经网络专家系统的设计与实现

智能型磨粒识别是铁谱技术发展的主要趋势,人工神经网络技术的出现为这种智能化提供了一条崭新的途径。介绍神经网络专家系统的基本原理,叙述BP学习算法,设计基于该算法的磨粒识别神经网络专家系统,并予以实现。     

�����׹��Ƶ��й�����ҵ��չ���ڲⶨ

物流业作为宏观经济的组成部分,其发展存在一定的周期性波动,揭示物流业发展的周期规律,测定其波动周期,具有一定的理论和实践意义。中国物流统计数据缺乏,客观上限制了对其周期规律的研究,本文选取社会物流总额作为测度指标,设计了一种人工序列,解决了统计数据过短问题;谱估计法从频域角度揭示客观事物的时间特性,在研究时间序列周期波动方面具有时域分析法所不具备的优势,作者采用谱估计法对中国物流发展周期进行测定,检验了指标序列平稳性,分析了截断点参数灵敏度,比较了6种不同滞后窗下周期值,并检验了所测得周期的显著性。研究表明,中国物流业发展在0.001显著水平下存在2个周期波动,分别是周期约为15.2年的长周期强波动和周期约为3.4年的短周期弱波动。     

地铁双线隧道施工人工冻结水热力数值分析

为了准确分析地铁隧道人工冻结施工过程中的热力学状况,考虑水分迁移和冰水相变耦合影响以及水泥水化热的生成,采用热蠕变本构建立了地铁隧道人工冻结施工的水热力耦合分析模型.对广州地铁某双线隧道施工过程中的热力状况进行了数值模拟,同时应用人工冻土的长期强度对冻结壁安全性进行了评估.分析结果表明:在地铁冻结法施工时,最大主应力沿着冻结管呈环形分布,并且管周围的应力明显偏高;开挖对环形应力场的影响不大,而且与其他施工方法不同,人工冻结法施工引起的地表沉降并不随开挖断面的逐渐扩大而增大,整个施工过程中的最大地表沉量仅为9.1 mm,因而人工冻结法施工能有效地控制地表沉降量.     

人工神经网络训练样本的相容性检测及化简

针对人工神经网络的训练样本庞大繁杂的特点,运用粗糙集理论对有指导的网络训练样本的相容性及其化简进行简单论述,同时对神经网络的特征值提取给出了一种寻找方法．     

CASE STORAGE BASED ON RELATIONAL DATABASE

IntroductionCase- Based Reasoning ( CBR) ,as a relativelynew methodology,has attracted wide concern ofAI researchers since1 980 's.The number of suc-cessful applications of CBR is growing rapidly,especially in the fields of architecture and indus-try,e.g. ARCHI- II[1] for the architecture designof courthouse and MIDAS[2 ] for the conceptualdesign of aircraft.The currently prevailing CBD systems mostlytreat cases as instances of some predeterminedand static case template.Such an appro…     

AN INTERNATIONAL VIEW OF DIFFERENT APPROACHESFOR FAULTS DETECTION AND IDENTIFICATIONIN NUCLEAR POWER PLANTS

IntroductionSafe,reliable and economical operation is thegoal of any industrial process control system,particularly in nuclear power industry,wherecatastrophic events can have severe economic andsafety consequences and where even small degra-dation in plant performance can result in largereplacement power costs.After the TMI acci-dent in1 979,a large number of computer- baseddiagnostic systems have been proposed to sup-port nuclear power plant ( NPP) operators.Theearly diagnostic approaches …     

智能化数据挖掘方法综述

数据挖掘被产业界认为是数据库系统最重要的前沿课题之一,是数据库技术、人工智能、机器学习等多学科相结合的产物。介绍了智能数据挖掘方法的研究现状及存在的问题,包括数据挖掘的定义、数据挖掘的任务;指出了数据挖掘研究的挑战性以及今后的发展方向。     

Disruption management in public transit: the bee colony optimization approach

Disruptions in carrying out planned bus schedules occur daily in many public transit companies. Disturbances are often so large that it is necessary to perform re-planning of planned bus and crew activities. Dispatchers in charge of traffic operations must frequently find an answer to the following question in a very short period of time: How should available buses be distributed among bus routes in order to minimize total passengers' waiting time on the network? We propose a model for assigning buses to scheduled routes when there is a shortage of buses. The proposed model is based on the bee colony optimization (BCO) technique. It is a biologically inspired method that explores collective intelligence applied by honey bees during the nectar collecting process. It has been shown that this developed BCO approach can generate high-quality solutions within negligible processing times.     

A novel forecasting approach inspired by human memory: The example of short-term traffic volume forecasting

Short-term traffic volume forecasting represents a critical need for Intelligent Transportation Systems. This paper develops a novel forecasting approach inspired by human memory, called the spinning network (SPN). The approach is then used for short-term traffic volume forecasting, utilizing a data set compiled from real-world traffic volume data obtained from the Hampton Roads traffic operations center in Virginia. To assess the accuracy of the SPN approach, its performance is compared to two other approaches, namely a back propagation neural network and a nearest neighbor approach. The transferability of the SPN approach and its ability to forecast for longer time periods into the future is also assessed. The results of the performance testing conducted in this paper demonstrates the superior predictive accuracy and drastically lower computational requirements of the SPN compared to either the neural network or the nearest neighbor approach. The tests also confirm the ability of the SPN to predict traffic volumes for longer time periods into the future, as well as the transferability of the approach to other sites.