神经网络在车辆半主动控制中的应用

针对车辆半主动悬挂模型的非线性特性，研究了采用神经网络的自适应控制在车辆悬挂半主动控制中的应用，设计了采用前馈神经网络的辩识器和控制器，对控制器网络采用的学习规则进行了分析。仿真计算表明，采用神经网络自适应控制方法能有效改善车辆的平稳性，采用的神经网络辩识器和控制器的改进BP算法是有效的。     

环氧化酶-2及表皮生长因子受体在非小细胞肺癌组织中的表达及临床意义

目的探讨环氧化酶-2(COX-2)与表皮生长因子受体(EGFR)在非小细胞肺癌(NSCLC)组织中的表达及与肺癌发生发展的关系。方法采用免疫组化(SP)法检测56例NSCLC和20例正常肺组织中COX-2与EGFR的表达。结果56例NSCLC组织中,COX-2与EGFR表达阳性率分别为64.2%和67.8%,显著高于正常肺组织(P<0.01),COX-2与EGFR表达与临床分期、病理分级、组织学分型和淋巴结转移密切相关(P<0.05),肿瘤分期愈晚,细胞分化越差,淋巴结转移越高,COX-2与EGFR表达阳性率越高,腺癌中COX-2表达明显高于鳞癌,鳞癌中EGFR表达高于腺癌(P<0.05)。结论COX-2与EGFR在NSCLC中异常表达说明其在肺癌发生发展中有重要作用,可作为判断NSCLC的生物学行为及估计预后的指标。     

质子交换膜燃料电池接触电阻研究进展

质子交换膜燃料电池(PEMFC)接触电阻问题是制约其商业化发展的一个重要因素。影响接触电阻的因素可归纳为电池材料、组装参数、工作参数和其他因素。本文主要介绍了PEMFC的接触电阻及其影响因素,并综述了降低接触电阻的方法。     

Modeling traffic operation at signalized intersections without explicit left‐turn yielding rules with an enhanced cell transmission model

This paper presents an enhanced cell transmission model (CTM) to capture traffic operation at signalized intersections without explicit permissive left‐turn yielding rules (i.e. aggressive permissive left‐turn maneuvers may not necessarily yield to opposing through traffic), which can be widely observed in many developing countries. Different from previous studies that focus on traffic dynamics on approaching links, this study contributes to modeling traffic operations within the intersection. A novel cell transmission framework with various types of virtual cells is proposed to model the dynamics of traffic movements from approach to exit. The unique phenomenon of competitive occupying of the conflict point between the left turn and opposing through movements is modeled. The cell state indicating its blockage is proposed to capture the dynamic queue formulation and dissipation and to evaluate the operational traffic performance at the intersection. Field validation results show that the proposed model can capture the operation of traffic at signalized intersections without explicit permissive left‐turn yielding rules with significantly higher level of accuracy than traditional traffic flow models. Copyright © 2016 John Wiley & Sons, Ltd.     

Practicability study on the suitability of artificial,neural networks for the approximation of unknown steering torques

For steer-by-wire systems, the steering feedback must be generated artificially due to the system characteristics. Classical control concepts require operating-point driven optimisations as well as increased calibration efforts in order to adequately simulate the steering torque in all driving states. Artificial neural networks (ANNs) are an innovative control concept; they are capable of learning arbitrary non-linear correlations without complex knowledge of physical dependencies. The present study investigates the suitability of neural networks for approximating unknown steering torques. To ensure robust processing of arbitrary data, network training with a sufficient volume of training data is required, that represents the relation between the input and target values in a wide range. The data were recorded in the course of various test drives. In this research, a variety of network topologies were trained, analysed and evaluated. Though the fundamental suitability of ANNs for the present control task was demonstrated.     

汽车车内噪声有源控制技术

有源噪声控制技术是目前国内外噪声控制界的研究热点。对有源噪声控制的概念、原理和实现作了介绍。根据有源控制方法对于低频噪声控制的优势,结合车内噪声的特点和现代控制领域的理论发展,讨论了在车内应用有源噪声控制技术的可行性,提出了一条可行的技术路线。     

BP神经网络在路面模量反分析中的应用

使用MATLAB神经网络工具箱研究了BP神经网络在路面模量反分析中的应用。研究结果表明,只要合理的处理输入和输出参数,利用BP神经网络可以较好的预测路面各层的弹性模量,并且相对于其他分析方法,该方法运算速度非常快,适合于实际工程中应用。     

电动汽车技术发展趋势及前景（下）

4燃料电池电动汽车 早在1839年．英国人格罗孚就提出了氢和氧反应发电的原理。20世纪60年代,研发出了液氢和液氧发电的燃料电池．由美国UTC公司首先用于航天和军事用途。近20年来．由于石油危机和大气污染日趋严重．以质子交换膜为代表的燃料电池技术．受到世界各国普遍重视。各大汽车公司纷纷投入巨资．研发出了各种类型的燃料电池电动汽车（FCEV）．     

基于神经网络的公交客流预测

公交客流量具有动态性,受多种因素的影响,不能或无法用精确的数学模型进行预测。通过对公交客流量预测的Elman和BP神经网络的建立、学习和训练。并以前三年的公交客流量、国内生产总值、工业总产值、城市人口数作为两种神经网络的输入神经元,第四年的公交客流量作为输出神经元,同时以合肥市公交客流量为例进行分析,结果表明：所建的Elman模型比EBP模型的预测精度高,效果好。     

不等时距GM(1,1)模型预测地基沉降研究

分别采用直线插值、三次样条插值、BP神经网络3种方法,用M ATLAB语言编制程序将不等时距序列转化为等时距序列,采用灰色理论预测沉降.由于BP神经网络强大的非线性映射功能,可以避免常规插值法所造成的一系列误差.实际工程应用结果表明,利用直线插值、三次样条插值和BP神经网络与灰色理论联合建模所得的预测值与实测值的最大相对误差分别为17.2%,5.9%和4.6%.由此可见BP神经网络和灰色理论联合建立的GM(1,1)模型用于预测路基沉降最为精确.