多电机机器人低成本神经脉冲PID控制研究

针对传统连续PID控制器并行使用导致资源访问阻塞,在单一设备内并行运行难以实现实时控制的问题,提出了一种基于神经脉冲的PID控制器,并实现了多电机的控制。该控制器将驱动和传感器信息作为脉冲,通过专门电路实时处理脉冲,实现了大规模的并行信息处理。实验结果证明了实现基于尖峰的控制器的可行性,且硬件要求较低,允许在大量并行控制器中复制该控制器,从而实现机器人实时控制。     

Estimating wall deflections in deep excavations using Bayesian neural networks

In this study, a neural network algorithm has been used to model the soil-structure interaction behavior of deep excavations in clays. The hybrid evolutionary Bayesian back-propagation (EBBP) neural network was used in this study and utilizes the genetic algorithms and gradient descent method to determine the optimal parameters within a Bayesian framework to regularize the complexity of learning and to statistically reflect the uncertainty in data. The EBBP analysis was carried out on an extensive database of braced excavation performance from finite element analyses. Additional parametric studies indicate that the model gives logical and consistent trends. Back-analyses of some instrumented case histories from the literature also indicate that the trained neural network model gives reasonable predictions in comparison to the actual measured values. The trained model can serve as a simple and reliable prediction tool to enable estimates of maximum wall deflection for preliminary design of braced excavations in clay. The model is able to take into consideration various factors such as the wall stiffness, support stiffness, the in-situ stress state, non-homogeneous soil conditions, and the variation of soil properties with depth. An added advantage of this approach is that it provides meaningful error bars for the model predictions.     

Frameworks, Networks and the UK Regional Agenda: nature planning for landscapes?

Planning at the landscape scale in Britain has had limited application. The origins, implementations and likely outcomes of new approaches to nature planning in Britain in which the spatial scale of planning could be 'landscape enabled' are traced. These approaches are termed 'framework' strategies, within which 'ecological networks' can be developed in order better to reflect species' behaviour and to overcome the restrictions of designation-based nature conservation. Currently, planning structures are subject to change and debate: published planning documents and other sources are examined for a case study of the North West of England, where experiments in ecological networks are underway. Evidence is sought for the incorporation into new planning structures of key concepts relevant to the achievement of network implementation. Evaluation is made of likely critical 'pinch points' in implementation using experience of network planning in the Netherlands for comparison. These include availability of data on habitats and species, the relationship of planning to agriculture, and the need for co-operation from stakeholders.     

基于神经网络的结构近似分析

在结构优化设计中经常会遇到结构分析次数多 ,计算量大的问题 ,如果每次迭代过程中都利用有限元方法 ,将是非常耗时的工作。为此 ,本文提出了一种BP神经网络进行结构近似分析的方法 ,通过对算例的计算表明 ,该方法是有效的     

结构优化设计中神经网络方法的应用

指出了传统优化设计方法的不足 ,概述了人工神经网络的基本特征和学习规则 ,提出了结构优化问题的神经网络方法设计原理和步骤 ,综述了对神经网络在结构优化中的应用。最后 ,研究了神经优化计算下一步需解决的难题     

高性能混凝土配合比设计中神经网络方法的应用

本文介绍了神经网络BP算法 ,并应用于实验室配制的高性能混凝土配合比中 ,结果证明该方法应用于高性能混凝土的配合比设计中是可行的。本文最后指出神经网络在高性能混凝土的配合比优化设计中 ,也将会有广阔的应用前景     

Job Search Networks and Strategies in Scattered-site Public Housing

How does poverty dispersal influence the job search tactics and networks of poor women? Using the results of interviews with 253 women living in dispersed and small clusters of public housing, this paper examines how job networks and search tactics may vary. The premise is that the mechanisms involved in connecting poor residents of more affluent areas with opportunity may consist of both social connections and new strategies for accessing opportunity. The paper finds that dispersed residents have job networks containing more diverse information. Second, dispersed residents more often used formal methods to find their most recent job. Third, dispersed residents seek better jobs, net of demographic controls, search method, and search outcome. The paper discusses the implications of these findings for the design of housing mobility and mixed-income housing programmes, the current policy emphasis at the US Department of Housing and Urban Development.     

金矿围岩稳定性分类指标的确定方法研究

基于金矿围岩稳定性影响指标分析,结合节点权重贡献率原理,建立BP网络模型,计算各个输入神经节点权值占整个输入神经节点权重比例大小,确定其每个影响指标对围岩分类的影响程度,按输入神经节点权重贡献率从大到小进行排序,最终确定出关键神经节点,并将其作为分类主要指标,从而提高建模精度.实验表明:这种方法用于确定金矿围岩稳定性分类指标具有较高的预测精度,能够满足分类的要求.     

灰色组合模型在坝体水平位移预测中的应用

在灰色预测的基础上,引入BP神经网络模型,建立了GM（1,1）和BP神经网络组合模型,分别运用GM（1,1）模型、BP神经网络模型和它们的组合模型三种模型对坝体的非线性水平位移进行了分析,对比发现此组合模型兼有灰色预测和BP神经网络预测的优点,模型既克服了原始数据少的缺点,也增强了预测的自适应性,证明了组合模型的预测精度较高,可以应用于坝体水平位移的预测。     

计及需求响应的Elman-NN短期负荷预测模型研究

通过频谱分析研究了需求响应负荷的基本特性,并以此为依据建立了计及需求响应的Elman神经网络(Elman-NN)预测模型。Elman-NN具有处理动态信息能力强、训练时间短、全局寻优性强的优点。通过实际算例,对比在Elman-NN模型中计及需求响应因素前后的预测性能,结果显示计及需求响应因素可显著提高Elman-NN模型预测精度。本文证实了在模型中计及需求响应因素的重要作用,为需求响应负荷的预测研究奠定了必要的理论基础。