基于灵敏度分析的海洋油气资源BP神经网络预测模型的优化

作者针对BP神经网络结构设计中存在的问题,提出利用灵敏度分析方法对BP神经网络预测模型进行优化。通过BP算法与参数灵敏度分析的结合,寻找网络输入属性与输出属性之间的影响因子;在保证精度的前提下优选网络输入属性,简化网络结构,以增强网络的泛化能力,减少人为主观因素对网络设计的影响。最后以海洋油气资源预测为例,结合实测资料建立BP神经网络预测模型并进行了优化及预测精度评价,表明优化后的模型既能有效提高油气资源预测结果的稳定性,又不损失预测精度。     

半潜平台浮子式系泊系统参数优化研究

通过在系泊缆中设置浮子可以改善系泊系统性能,降低平台运动响应。建立浮子式系泊系统的数值计算模型,验证浮子式系泊系统数值计算方法,详细分析浮子设计参数(设置位置和净浮力大小)变化对系泊缆张力特性与平台运动的影响规律,并根据得到的规律选择了优化的浮子系泊系统方案。最后对优化方案进行评估,表明优化方案可以显著降低系泊中的平台水平运动,尤其是低频运动,同时系泊缆张力变化不大,仍满足安全要求。研究结果可为今后浮子式系泊系统设计提供参考。     

A parallel algorithm for coverage optimization on multi-core architectures

Location siting is an important part of service provision, with much potential to impact operational efficiency, safety, security, system reliability, etc. A class of location models seeks to optimize coverage of demand for service that is continuously distributed across space. Decision-making and planning contexts include police/fire resource allocation for a community, siting cellular towers to support cell phone signal transmission, locating emergency warning sirens to alert the public of severe weather and other related dangers, and many others as well. When facilities can be sited anywhere in continuous space to provide coverage to an entire region, this is a very computationally challenging problem to solve because potential demand for service is everywhere and there are an infinite number of potential facility sites to consider. This article develops a new parallel solution approach for this location coverage optimization problem through an iterative bounding scheme on multi-core architectures. The developed approach is applied to site emergency warning sirens in Dublin, Ohio, and fire stations in Elk Grove, California. Results demonstrate the effectiveness and efficiency of the proposed approach, enabling real-time analysis and planning. This work illustrates that the integration of cyberinfrastructure can significantly improve computational efficiency in solving challenging spatial optimization problems, fitting the themes of this special issue: cyberinfrastructure, GIS, and spatial optimization.     

Estimating spatial efficiency using cyber search,GIS, and spatial optimization: a case study of fire service deployment in Los Angeles County

ABSTRACT

The efficiency of public investments and services has been of interest to geographic researchers for several decades. While in the private sector inefficiency often leads to higher prices, loss of competitiveness, and loss of business, in the public sector inefficiency in service provision does not necessarily lead to immediate changes. In many cases, it is not an entirely easy task to analyze a particular service as appropriate data may be difficult to obtain and hidden in detailed budgets. In this paper, we develop an integrative approach that uses cyber search, Geographic Information System (GIS), and spatial optimization to estimate the spatial efficiency of fire protection services in Los Angeles (LA) County. We develop a cyber-search process to identify current deployment patterns of fire stations across the major urban region of LA County. We compare the results of our search to existing databases. Using spatial optimization, we estimate the level of deployment that is needed to meet desired coverage levels based upon the location of an ideal fire station pattern, and then compare this ideal level of deployment to the existing system as a means of estimating spatial efficiency. GIS is adopted throughout the paper to simulate the demand locations, to conduct location-based spatial analysis, to visualize fire station data, and to map model simulation results. Finally, we show that the existing system in LA County has considerable room for improvement. The methodology presented in this paper is both novel and groundbreaking, and the automated assessments are readily transferable to other counties and jurisdictions.     

Optimal routing for waste collection: a case study in Singapore

ABSTRACT

To collect and dispose growing amounts of municipal solid waste (MSW) changed to be a hot topic along with the rapid urbanization in past decades. Cities are more and more dependent on the incineration instead of landfilling due to the cost-efficiency and environmental concerns. Considering the limited number of incineration plants and complicated situation of transportation in both spatial and temporal dimensions in different cities, the optimal routing for waste collection turns to be meaningful research topic. In this research, the ant colony optimization (ACO)-based multi-objective routing model coupled with min-max model and Dijkstra’s algorithm is proposed to address the question of which route to take from these waste-generating points to the target incineration plant(s) considering travel time, accident probability (black spots), and population exposure, so as to support the routing decision-making. The model is successfully implemented in Singapore and the effectiveness of the model has also been justified. Besides, few limitations of this research have also been discussed, some of which would also be the future directions of our research, especially the design and integration of a web-based routing decision-making support system.     

脐带缆在潜器下放过程中的运动建模与仿真

潜器在下放布置过程中需要考虑变长度的脐带缆对其运动的影响,在考虑流的情况下,对脐带缆的有限差分模型进行了改进,并采用最小二乘方法求解由时间和空间上的中心差分格式离散后的非线性方程组。为了验证模型改进的有效性,将潜器在均匀定常流中水平匀速直航时的数值解与该特殊情况下的解析解进行比较,两组解的吻合不仅证实了模型改进的有效性,而且表明上述数值计算方法是可靠且有效的。在潜器下放布置运动给定的情况下,脐带缆的运动仿真结果表明,潜器姿态角的调整会对拖曳点处的缆绳张力大小和变化趋势产生显著的影响,流在改变缆绳空间形状的同时引起了缆绳对潜器作用力和力矩的非线性和时变性,脐带缆总是阻止潜器自身动力对运动速度和姿态角的改变,且对纵荡运动的影响最大。     

页岩气基础地质调查皖南地1井钻探施工技术

皖南地1井是部署在安徽省南陵县烟墩镇的一口页岩气基础地质调查井。文章详细介绍了该井的钻探施工工艺技术以及遇到复杂问题的处理方法,并对钻效进行了分析,提出了实现优质高效钻探的措施。项目的顺利实施,梳理了皖南地区地层层序,为页岩气储层理论推测提供了有力的实物数据支撑和验证。     

Geometric-constrained multi-view image matching method based on semi-global optimization

Targeting at a reliable image matching of multiple remote sensing images for the generation of digital surface models, this paper presents a geometric-constrained multi-view image matching method, based on an energy minimization framework. By employing a geometrical constraint, the cost value of the energy function was calculated from multiple images, and the cost value was aggregated in an image space using a semi-global optimization approach. A homography transform parameter calculation method is proposed for fast calculation of projection pixel on each image when calculating cost values. It is based on the known interior orientation parameters, exterior orientation parameters, and a given elevation value. For an efficient and reliable processing of multiple remote sensing images, the proposed matching method was performed via a coarse-to-fine strategy through image pyramid. Three sets of airborne remote sensing images were used to evaluate the performance of the proposed method. Results reveal that the multi-view image matching can improve matching reliability. Moreover, the experimental results show that the proposed method performs better than traditional methods.     

A geometric-based approach for road matching on multi-scale datasets using a genetic algorithm

Object matching is used in various applications including conflation, data quality assessment, updating, and multi-scale analysis. The objective of matching is to identify objects referring to the same entity. This article aims to present an optimization-based linear object-matching approach in multi-scale, multi-source datasets. By taking into account geometric criteria, the proposed approach uses real coded genetic algorithm (RCGA) and sensitivity analysis to identify corresponding objects. Moreover, in this approach, any initial dependency on empirical parameters such as buffer distance, threshold of spatial similarity degree, and weights of criteria is eliminated and, instead, the optimal values for these parameters are calculated for each dataset. Volunteered geographical information (VGI) and authoritative data with different scales and sources were used to assess the efficiency of the proposed approach. According to the results, in addition to an efficient performance in various datasets, the proposed approach was able to appropriately identify the corresponding objects in these datasets by achieving higher F-Score.     

基于优化经验模态分解和聚类分析的滑坡位移智能预测研究

针对三峡库区"阶跃式"滑坡的变形特征,提出了一种新的滑坡位移预测方法。以白水河滑坡ZG118和XD-01监测点位移数据为例,采用基于软筛分停止准则的经验模态分解(SSSC-EMD)将累计位移-时间曲线和影响因子时间序列自适应地分解为多个固有模态函数(IMF),并采用K均值(K-Means)聚类法对其进行聚类累加,得到有物理含义的位移分量(趋势性位移、周期性位移以及随机性位移)和影响因子分量(高频影响因子和低频影响因子)。使用最小二乘法对趋势性位移进行拟合预测;采用果蝇优化-最小二乘支持向量机(FOA-LSSVM)模型对周期性位移和随机性位移进行预测。将各位移分量预测值进行叠加处理,实现滑坡累计位移的预测。研究结果表明,所提出的(SSSC-EMD)-K-Means-(FOA-LSSVM)模型能够预测"阶跃式"滑坡的位移变化规律,且预测精度高于传统的支持向量机回归(SVR)、最小二乘支持向量机(LSSVM)模型;并通过改变训练集长度,进行单因素分析,发现其与预测精度之间呈正相关关系。