联合BP神经网络和粒子群的结构有限元模型修正

为解决有限元模型修正中寻优速度慢和算法易于陷入局部最优的问题,提出了采用BP神经网络作为代理模型,采用粒子群算法作为优化算法的模型修正方法。为验证算法的有效性和高效性,采用所提方法对一个钢桁架进行了模型修正,修正结果表明,所提算法能够准确找到结构损伤位置,并且对杆件的损伤程度的识别精度较高,并且与传统的直接调用有限元模型计算结构响应的方法对比,所提方法在寻优速度上具有明显提升。     

基于改进蚁群算法的钢结构优化设计

在介绍蚁群优化算法的原理、基本框架的基础上,提出了一种改进的蚁群算法——分层蚁群算法,并将该算法应用到钢结构优化设计中,最后通过一个算例验证了该方法的效率和有效性,结果表明该方法科学可行,具有很好的应用前景。     

聚类分析算法的分析与评价

聚类方法大体可以分为基于层次聚类算法、基于划分聚类算法、基于密度聚类算法、基于网格聚类算法、基于模型聚类算法、基于模糊聚类算法等。本文对主要聚类方法进行分析,并且结合具体的聚类分析算法进行聚类评价。     

基于C语言的“穷举”与“递推”算法的研究

结合实际问题对"穷举"和"递推"算法的基本思想进行分析,研究算法的实现方法,借助C语言将算法转化为可执行的程序代码。"穷举"算法的关键是找到数据的测试范围和测试标准,并对测试标准的转化技巧、测试范围的控制方法进行了阐述。"递推"算法的归结到对递推初值、递推法则、递推次数三个条件的研究,并从顺推、逆推两个方向分别进行了阐述。     

基于自适应任务粒度控制的Prony算法的并行优化

因为Prony算法难以根据其结构特征实现静态负载均衡以及任务分配,所以其需要根据其特征实现自适应任务粒度并行。本文提出了基于自适应任务粒度控制系统(ATGCS)的Prony算法,重点研究Prony算法的自适应调度方法。此方法利用ATGCS实现Prony算法的并行化,并针对性提出高效计算的优化方法,提高Prony算法的计算速度。实验结果显示本方法相对于现有方法具有更好的性能。     

一种改进的灭火救援路径规划理论与实现

对经典的最短路径算法进行分析,结合人工智能领域的启发式搜索,给出一个基于启发式的最短路径算法。对该算法从代价函数和排序方法方面提出了改进策略。仿真实验数据表明,该方法优于经典的最短路径算法,能够有效地缩短路径查找时间,从而提高灭火救援的效率。     

岩土工程参数反演的一种新方法

介绍了新近提出的一种模拟进化算法——粒子群算法,相对于其他进化算法,粒子群算法的优势在于简单、易实现且收敛快。把该算法引入岩土工程参数反演领域,同时为了克服粒子群算法后期搜索效率降低的缺陷,把单纯形法嵌入到粒子群算法中,提出岩土工程参数反演的一种新方法——基于粒子群算法和单纯形法的混合算法。算例表明,混合算法在参数反演计算中体现出良好的优化性能和很快的收敛速度,是一种新颖可行的参数反演方法。     

基于Ncut的自适应图像分割方法

为了解决传统归一化割(Normalized cut,Ncut)算法需要人工干预因素过多,限制了算法的通用性,本文对传统Ncut算法进行了改进,提出了自适应的图像分割方法。首先采用基团势的理论替代了传统的Ncut算法中计算权值矩阵时两个控制参数对结果的影响;然后为了减少K-means算法对分类数目和类中心的敏感,本文采用基于最小生成树的聚类方法对Ncut计算出的特征向量进行分类,得到最终的分类数目和初始类中心,然后再采用K-means算法进行聚类得到最终的分割结果。实验结果显示,本文的算法不仅提高了算法的通用性,并且分割效果比较好。     

一种指纹图像预处理方法的研究

实现一套指纹图像预处理算法,主要包括指纹图像灰度归一化和均衡化、指纹图像分割、指纹图像的二值化、指纹图像增强、指纹图像细化。采用基于梯度的指纹图像分割方法,去除指纹图像中的无用信息,并使用连通域检测方法对分割后的指纹图像进行优化。引入基于动态阈值法的二值化算法,实现指纹图像的方向二值化。采用基于骨架提取技术的细化算法,完成指纹图像的细化处理。最后使用MATLAB8.2平台对该算法进行验证,在相同特征提取算法和匹配条件下,该算法的识别精度高于传统算法。     

基于机器学习的火灾事故等级分类研究

为了探究火灾的严重程度与消防队响应时间、救援人数、火灾地点、火灾探测器以及自喷系统等之间的关系,采用随机森林、人工神经网络、支持向量机和极限学习机4 种机器学习算法对美国旧金山市的历史火灾数据进行了挖掘分析。运用模糊理论将消防队响应时间和救援人数转换为三角模糊数,提出了一种基于模糊推理的火灾因素分类方法。研究发现4 种算法的准确率均超过90％,并通过交叉验证的方法证明了这些算法的可靠性。在4 种算法中,随机森林算法的准确率和Kappa 值均高于其他算法,但是其计算得到的第三类火灾的AUC 值最小。     

多任务在多顺序加工场所作业排序的微机实现

对多任务在多顺序加工场所作业排序的两种常用近优算法──贝氏法和参数法，以及近年提出的4种序权算法──序权法、个别作业比率序权法、个别加工场所的约翰逊规则序权法和扩展的贝氏规则序权法，进行了计算机综合模拟、分析，并给出了选优结果。     

智能建筑中暖通空调系统控制方法初探

主要讨论了智能建筑中暖通空调系统目前的主要控制算法和控制方法，指出了它们在暖通空调控制系统中存在的缺陷；着重介绍了国内外几种较为先进的控制算法及控制方法，分析比较了它们的优缺点及应用场所，并指出了它们的发展方向及前景。     

Simulation‐based dynamic traffic assignment: Meta‐heuristic solution methods with parallel computing

The aim of this study is to solve the large‐scale dynamic traffic assignment (DTA) model using a simulation‐based framework, which is computationally a challenging problem. Many studies have been performed on developing an efficient algorithm to solve DTA. Most of the existing algorithms are based on path‐swapping descent direction methods. From the computational standpoint, the main drawback of these methods is that they cannot be parallelized. This is because the existing algorithms need to know the results of the last iteration to determine the next best path flow for the next iteration. Thus, their performance depends on the single initial or intermediate solution, which means they exploit a solution that satisfies the equilibrium conditions more than explore the solution space for the optimal solution. More specifically, the goal of this study is to overcome the drawbacks of serial algorithms by using meta‐heuristic algorithms known to be parallelizable and that have never been applied to the simulation‐based DTA problem. This study proposes two new solution methods: a new extension of the simulated annealing and an adapted genetic algorithm. With parallel simulation, the algorithm runs more simulations in comparison with existing methods, but the algorithm explores the solution space better and therefore obtains better solutions in terms of closeness to the optimal solution and computation time compared to classical methods.     

Computational design optimization: A review and future directions

A mathematical model for design optimization of engineering systems is defined. Computational algorithms to treat the model are reviewed and their features are discussed. The attributes of a good algorithm are given. Sequential quadratic programming algorithms that generate and use the approximate Hessian of the Lagrange function to calculate the search direction are the most recent methods. They are the most reliable methods among the available ones. Several other computational aspects, such as robust implementation of algorithms, use of a knowledge base, interactive use of optimization, and use of a database and database management system, are discussed. Recent developments in the field and future directions are presented.     

Analysis on the feasibility of multi-source remote sensing observations for chl-a monitoring in Finnish lakes

Chlorophyll-a (chl-a) concentration of lake water can be measured with airborne (or spaceborne) optical remote sensing instruments. The rmse obtained here with empirical algorithms and 122 measurement points was 8.9 microg/l (all points used for training and testing). Airborne Imaging Spectrometer for Applications (AISA) was used in four lake water quality measurement campaigns (8 measurement days) in southern Finland during 1996-1998 with other airborne instruments and extensive in situ data collection. As empirical algorithms are employed for chl-a retrieval from remote sensing data, temporally varying factors such as surface reflection and atmospheric effects degrade the estimation accuracy. This paper analyzes the quantitative accuracy of empirical chl-a retrieval algorithms available as methods to correct temporal disturbances are either included or excluded. The aim is to evaluate the usability of empirical chl-a retrieval algorithms in cases when no concurrent reference in situ data are available. Four methods to reduce the effects of temporal variations are investigated. The methods are: (1) atmospheric correction; (2) synchronous radiometer data; (3) wind speed data; and (4) bidirectional scattering model based on wind speed and sun angle data. The effects of different correction methods are analyzed by using single-date test data and multi-date training data sets. The results show that the use of a bidirectional scattering model and atmospheric correction reduces the bias component of the measurement error. Radiometer data also appear to improve the accuracy. However, if concurrent in situ reference data are not available, the retrieval algorithms and correction methods should be improved for reducing the bias error.     

交通分配中转向流量的直接计算方法

提出交通分配中在得到路段流量的同时可直接计算转向流量的两种方法,前者基于转向-路径关系适用于给出具体路径构成的交通分配算法,后者基于转向-路段关系适用于Dial算法。这两种转向流量的直接计算方法能避免传统的Furness、Fratar等推算法及扩展网络法的缺陷,能应用于大部分常见的交通分配算法,其有效性通过算例得到证实。     

蚁群算法在GIS最短路径求解中应用的初步研究

最短路径的求解是GIS应用中的主要问题之一。在传统的最短路径求解算法中,Dijkstra算法和启发式搜索算法-A＊算法具有较好的效果,得到了广泛的应用。蚁群算法是由意大利学者Dorigo等人于20世纪90年代初期通过模拟自然界中蚂蚁集体寻径的行为而提出的一种基于种群的启发式仿生进化系统。蚁群算法最早成功应用于解决著名的旅行商问题,该算法采用了分布式正反馈并行计算机制,易于与其他方法结合,而且具有较强的鲁棒性,是一种很有前途的仿生优化算法。本文将对该算法应用于GIS中最短路径的求解方面的问题进行初步的研究。     

On the efficiency of quantization-based integration methods for building simulation

Models describing energy consumption, heating, and cooling of buildings usually impose difficulties to the numerical integration algorithms used to simulate them. Stiffness and the presence of frequent discontinuities are among the main causes of those difficulties, that become critical when the models grow in size. Quantized State Systems (QSS) methods are a family of numerical integration algorithms that can efficiently handle discontinuities and stiffness in large models. For this reason, they are promising candidates for overcoming the mentioned problems. Based on this observation, this article studies the performance of QSS methods in some systems that are relevant to the field of building simulation. The study includes a performance comparison of different QSS algorithms against state-of-the-art classic numerical solvers, showing that the former can be more than one order of magnitude faster.     

New methods for reducing the number of false alarms in fire detection systems

In this paper, we present new methods of reducing the number of false alarms in smoke detectors and apply these methods to an ionization smoke detector. The detector is able to diagnose its working condition and its environment very precisely. When the detector's environment changes, the detector can automatically determine the cause, whether the change is fire-related or not. This is done by measuring the ionization current in two sensitivity ranges of the measurement chamber and analyzing the results with new algorithms. With the help of algorithms that use fuzzy logic, we can identify basically every potential problem an ionization detector can produce.     

自由度匹配技术在框架结构损伤识别中的应用研究

实测自由度与理论自由度不匹配是结构损伤识别技术应用于实际工程中的一大难题,模型缩聚和模态扩阶技术是解决这一问题的主要方法。通过单层框架结构有限元模型的数值模拟,利用振型转角差损伤识别方法,较好地实现了测试信息不完备情况下的框架结构损伤识别。结果表明,利用Guyan减缩法与模态扩阶法进行自由度匹配后再进行损伤识别,其结果非常准确,可以应用于框架结构的损伤识别。