计算智能技术在工程中的应用

计算智能技术主要包括人工神经网络、演化计算和模糊系统等智能模拟方法,它们分别从不同的角度实现对人类智能的模拟。文章首先讨论了计算智能技术所包含的这几种智能模拟方法在工程中的应用,然后对应用过程中各方法的优势和问题、潜力和局限进行了详细的分析,最后给出了相应的解决办法。     

构筑动态神经网络结构的一种途径

如何决定人工神经网络的适当规模，以往都是通过试探法来实现，不但费时，而且无规律可循。本文基于神经网络的基本学习算法，构筑动态网络结构，使之更符合抽取的新的输入、输出特性。     

基于改进型遗传算法的神经网络参数优化

针对标准遗传算法的不足，文中提出一种改进型遗传算法，它将标准遗传算法和BP算法有机结合，兼具了标准遗传算法的全局搜索和BP网络局部精确搜索的特征，并将其应用于船舶自动舵神经网络控制器的训练中，取得较满意的结果。     

具有自学习和自进化能力的人工鱼模型设计

将人工神经网络方法引入到“人工鱼”系统中，控制人工动物的行为，使人工动物成为更加自主的和智能的角色。同时，利用遗传算法，解决人工鱼的先天遗传进化和后天的学习进化的结合问题。     

Integrating scheduling and control functions in computer integrated manufacturing using artificial intelligence

Proper integration of scheduling and control in Flexible Manufacturing Systems will make available the required level of decision-making capacity to provide a flexibly-automated, efficient, and quality manufacturing process. To achieve this level of integration, the developments in computer technology and sophisticated techniques of artificial intelligence (AI) should be applied to such FMS functions as scheduling. In this paper, we present an Intelligent Scheduling System for FMS under development that makes use of the integration of two AI technologies. These two AI technologies — Neural Networks and Expert Systems — provide the intelligence that the scheduling function requires in order to generate goodschedules within the restrictions imposed by real-time problems. Because the system has the ability to plan ahead and learn, it has a higher probability of success than conventional approaches. The adaptive behavior that will be achieved contribute to the integration of scheduling and control in FMS.     

一种集成的智能网络故障管理结构

综合网络故障管理与人工智能的方法,在对现有几种用于故障诊断的人工智能方法的特点和局限性分析基础上,将集成人工智能技术引入网络故障管理领域,提出了一种基于多种人工智能技术集成的智能故障管理结构,该结构充分利用不同智能故障诊断技术的互补性,在一定程度上克服了现有故障诊断技术存在的局限性,改善了故障管理系统的性能。     

Artificial Neural Network estimation of wheel rolling resistance in clay loam soil

Despite of complex and nonlinear relationships imparting soil–wheel interactions, however, logical, non-randomized, and manifold relations tackle to express and model the interactions which are valid for variety of conditions and are likely to be established whereas mathematical equations are restricted to present. A 3-10-1 feed-forward Artificial Neural Network (ANN) with back propagation (BP) learning algorithm was utilized to estimate the rolling resistance of wheel as affected by velocity, tire inflation pressure, and normal load acting on wheel inside the soil bin facility creating controlled condition for test run. The model represented mean squared error MSE of 0.0257 and predicted relative error values with less than 10% and high coefficient of determination (R²) equal to 0.9322 utilizing experimental output data obtained from single-wheel tester of soil bin facility. These rewarding outcomes signify the fitting exploit of ANN for prediction of rolling resistance as a practical model with high accuracy in clay loam soil. Derived data revealed rolling resistance is less affected by applicable velocities of tractors in farmlands nevertheless is much influenced by inflation pressure and vertical load. An approximate constant relationship existed between velocity and rolling resistance implying that rolling resistance is not function of velocity chiefly in lower ones. Increase of inflation pressure results in decrease of rolling resistance while increase of vertical load brings about increase of rolling resistance which was measured to be function of vertical load by polynomial with order of two model validated by conventional models such as Wismer and Luth model.     

面向对象的遗传算法及其在神经网络辅助设计中的应用

在现有的遗传算法的基础上,采用面向对象技术设计了面向对象的遗传算法,建立了遗传算法的类层次。这种方法改变了在传统的遗传算法中各个函数之间只有参数的传递,而没有代码的继承性的状况从概念上提高了软件的可重用性。该方法在人工神经网络的辅助设计问题中的应用表明,这一算法由于采用面向对象的分析与设计方法,从而具有比传统的遗传算法更好的通用性,用户可以更方便地设计和实现自己的编码方案和遗传算子,大大提高了软件的可重用性。     

多模噪声中粒子滤波算法研究

粒子滤波是一种解决非高斯滤波问题的有效方法,受到许多领域的研究人员的重视。在扩展卡尔曼滤波(EKF)的基础上,提出一种基于多层感知器(MLP)的扩展卡尔曼滤波算法。利用扩展卡尔曼粒子滤波器和MLP对当前时刻状态重要性采样,引入MLP对样本进行重采样。该算法能有效利用测量值的最新信息,对状态估计的误差更小。在实验中,对于多模噪声非线性系统,该算法与另外算法进行比较。结果证明,所提算法性能优异于其他算法。     

智能型计算机网络考试评价系统开发工具

介绍了智能型计算机考试评价系统开发工具AUTO-KP的结构和功能。AUTO-KP特别适合于演绎类课程考评系统的开发,能完成考试工作的组卷、考试、阅卷、评讲和总结等全过程。     

人工神经网络在个人住房贷款信用评价中的应用

个人住房贷款在商业银行的业务中属于高风险的一种,因此,对贷款申请人进行信用评价极为重要。本文运用matlab软件,把人工神经网络与信用评价系统结合起来,贷款申请人的各项指标作为输入值,信用度为输出值,为科学评价个人信用提供了依据。     

一种基于神经网络的模糊方法研究

模糊系统设计中,模糊规则的建立是系统设计的瓶颈问题。针对这一问题,该文提出了一种用于监督神经网络自动生成模糊规则并实现模糊推理的方法。网络训练分为两个阶段,首先是结构学习,确定系统的规则总数和前提的有关参数;其次是参数学习,即调整权值,使系统输出接近理想输出。仿真实例证明使用该方法建立模糊系统具有较好的效果。     

Prediction of manually controlled vessels’ position and course navigating in narrow waterways using Artificial Neural Networks

Despite modern navigation devices, there are still some problems for navigating of vessels in narrow waterways because of geographical structures and various disturbances. In this study, a guidance and an early warning method by means of predicting three-minute-ahead position of a vessel, especially in the turning points, has been developed for navigating in narrow waterways. The Istanbul Strait has been specifically studied as a model. Since operators in Vessel Traffic Services (VTS) can watch only straight bearing of vessels on VTS panels but especially for turning regions, they have to foresee a risk on time which may result in a disaster. The objective of this study is to predict the future coordinates of a manually controlled vessel using Artificial Neural Networks (ANN).Artificial Neural Networks have been trained by using position and speed data collected from vessels which navigated manually in the Strait. Three-minute-ahead position of vessels has been predicted by using the trained ANN. Some on-line experiments have been done in Istanbul VTS centre and it has been observed that the method satisfied the goal in especially turning points of the Strait. Hence the proposed method could be utilized for warning system by VTS operators and guidance system by vessel crew.     

分布式集成信息系统中知识检索方法

支持产品设计的分布式集成信息系统中知识库是系统的核心,如何准确检索到所需知识对系统运行性能有重要影响.文章通过将人工神经网络、模糊理论和规则推理相结合提出了快速、有效的知识检索方法,并探讨了知识分层问题,以支撑件知识检索为对象开发了知识检索原型系统.文章旨在探讨一种合理、有效、快速的知识检索方法,为分布式集成信息系统的成功运行提供性能保障.     

环境智能中上下文推理方法研究综述

上下文推理是环境智能研究的核心问题之一,与环境智能系统的觉察、响应及适应能力紧密相关,近年来受到国内外研究者的广泛关注。文中分析介绍上下文推理的主要研究内容、研究方法和研究进展,并探讨目前存在的问题及未来的发展方向。     

多层前向神经网络在柴油机故障诊断系统中的应用研究

故障诊断是计算机模式识别领域的一个活跃课题。文中提出了基于ANN的柴油机故障诊断方法,设计了适合该诊断系统的BP网络结构,并给出了一种改进的BP算法(IBP),该算法基于黄金分割法自适应调整网络学习速率。仿真结果表明:该算法比标准BP算法具有更快的学习速度和更高的学习精度,完全适用于柴油机故障诊断系统。     

Air pollution modelling with the aid of computational intelligence methods in Thessaloniki, Greece

Air pollution modelling is necessary for simulating the atmospheric environment system in terms of pollutants and meteorological conditions, taking into account the nonlinearities of the underlying phenomena. In the current paper, Artificial Neural Networks are used for modelling ozone, and for simulating its behaviour in relation to other atmospheric parameters of interest, for the city of Thessaloniki, Greece. This behaviour is also investigated with the aid of Principal Component Analysis (PCA). Results suggest the operational capabilities of such models, and the research potential in the application of computational intelligence methods for the environmental sector.     

A Neural Network Constructing Method Based on Many Kinds of Neurons Model

In this paper, the geometrical meaning of the neurons in BPNN （Back Propagation Neural Network） and RBFNN （Radial Basis Function Neural Network） in the High Dimensional Space （HDS） is analyzed, and a new type of NN is built based on many kinds of neurons. This new NN solves the covering problem of the complex geometry shape in the high dimensional feature space which is raised by the Biomimetic Pattern Recognition （BPR）. This new NN-Constructing method has broken the traditional thinking mode of constructing NN which only uses one kind of neuron.     

A hybrid modeling approach for forecasting the volatility of S&P 500 index return

Forecasting volatility is an essential step in many financial decision makings. GARCH family of models has been extensively used in finance and economics, particularly for estimating volatility. The motivation of this study is to enhance the ability of GARCH models in forecasting the return volatility. We propose two hybrid models based on EGARCH and Artificial Neural Networks to forecast the volatility of S&P 500 index. The estimates of volatility obtained by an EGARCH model are fed forward to a Neural Network. The input to the first hybrid model is complemented by historical values of other explanatory variables. The second hybrid model takes as inputs both series of the simulated data and explanatory variables. The forecasts obtained by each of those hybrid models have been compared with those of EGARCH model in terms of closeness to the realized volatility. The computational results demonstrate that the second hybrid model provides better volatility forecasts.     

基于人工神经网络的大气质量智能评价预警系统的设计与应用

基于人工智能的神经网络技术,建立大气质量智能评价预警系统。该系统可以实现对大气污染物数据的自动分析及对大气质量的智能评价。通过局部大气的污染程度和运动趋势预测综合大气质量并实现预警。该系统能够为环境管理决策提供及时、准确、全面的环境质量信息,同时也可以帮助相关部门和企业对未来发展做出正确的决策。