机动车尾气排放测算行驶周期的自动建立方法

为了建立用于机动车尾气排放测算的行驶周期,利用便携车载尾气采集装置(PEMS)系统和GPS装置进行了大量的机动车尾气排放和驾驶活动数据采集,并对数据进行了预处理,提出了短行程的评价标准,给出了最优短行程自动搜索的2种启发式算法(遗传算法(GA)和离散同步扰动随机逼近(DSPSA)),对建立的行驶周期进行了预测尾气排放总量的有效性验证。结果表明：2种启发式算法均能有效地解决行驶周期自动建立问题,GA算法优化得到的行驶周期更有代表性,该行驶周期能以相对较小的误差预测尾气排放总量。建议将GA算法作为开发其他城市的行驶周期的算法工具。     

模式识别的斜拉桥损伤诊断动力指纹与识别算法

为有效并准确诊断出斜拉桥损伤,对基于模式识别的斜拉桥损伤诊断方法进行了研究。选取易于测试出的低阶模态频率和部分关键点竖向振型数据为动力指纹,无需模态扩展或模型缩聚。研究并采用全因子设计进行动力指纹库的创建,可精确评估设定的损伤因子及其交互作用对损伤识别结果的影响。设计并增加了带随机误差的动力指纹库样本集。编制了基于Matlab的模式识别的多种算法,重点研究了精确度高的多层感知器识别算法及其提高该算法预测准确率的装袋集成算法。最后给出一座单塔双跨双索面斜拉桥的多种识别算法的损伤诊断过程和结果,得到一种可包容测试随机误差的高精确度斜拉桥损伤诊断评估模型。     

前混合磨料射流磨料速度测试的新方法

前混合磨料射流超强的打击力主要是由高速磨料群提供的,因此,磨料速度测试是磨料打击力分布规律等研究的基础。针对传统研究方法的不足之处,笔者提出采用PIV技术结合自主编程设计的磨料中心识别程序,实现非接触式测试手段下磨料速度测试实验研究,并利用该方法简要分析了喷嘴结构对磨料速度的影响。结果表明,在一定范围内增加直线段长度有利于提高喷嘴出口处磨料的速度,表明在喷嘴直线段末端磨料依然处于明显的加速状态;增加收敛段长度对提高喷嘴出口处磨料速度有一定的作用,但磨料速度增幅不大;收敛角较大时,液相在收敛段前半段加速缓慢而在后半段过于剧烈,因磨料颗粒加速滞后于液相的原因导致喷嘴出口处磨料速度降低。     

基于近红外光谱的小麦品质分类研究

为了快速、简便、准确地鉴别小麦品质的类别,本研究提出了应用近红外光谱分析技术结合BP神经网络的鉴别方法对小麦进行品质分类。研究过程中对小麦样品的光谱数据进行了详细分析,采用马氏距离剔除了光谱数据中异常数据,并通过主成分分析说明利用近红外光谱鉴别小麦品质分类的可行性。为了提高所建模型的性能,采用SPXY算法对小麦样品进行合理的划分。并选取了一阶微分加归一化的预处理方法来处理光谱数据,消除无关信息和噪声对小麦光谱数据的影响。运用偏最小二乘法压缩光谱数据,减少了数据量,节省建模时间。最后采用BP神经网络方法建立了小麦品质分类模型。实验结果显示：模型的鉴别效果较好,对强筋样品识别的准确率高达94.4%,弱筋样品识别的准确率高达100%。实现了快速、准确地对小麦品质强筋和弱筋两类的鉴别,对小麦生产、市场交易及食品加工有着非常重要的意义。     

基于Visual c++矩形标尺智能识别

通过利用图像处理和图像识别领域的边界分割Robert局部边缘检测算子方法及梯度算子区域迭代的阈值图像分割算法相结合来对图像特征进行二次提取,不同于单独采用边界分割与区域分割算法,该算法通过对边缘检测结果的差分结果的迭代分析,有效的增强了识别算法对识别条件的适应性及识别精度,并采用Visual C 编程进行计算机图像辅助设计作为实现手段.     

履带式拖拉机自动驾驶系统路径智能跟踪控制研究

为实现复杂环境下履带式拖拉机田间作业的路径跟踪控制,设计了履带式拖拉机自动驾驶系统,并对路径跟踪与控制算法进行了研究。自动驾驶系统由MCU、双源激光定位系统、速度控制系统、点火/熄火控制系统、液压转向系统等组成。采用模糊算法对行驶过程中的路径偏差进行补偿,实现对路径的跟踪控制。为验证算法的有效性,进行了Matlab/Simulate仿真与田间试验。结果显示对于NF502型履带拖拉机,该系统在100 m范围内可实现有效控制,表明该算法能实现对行驶路线跟踪与控制。     

大豆水溶性蛋白含量测定的不确定度评定

建立大豆水溶性蛋白含量测定（NY/T 1205-2006）不确定度评定的数学模型,对检测过程中带来的各个不确定度分量进行识别和量化,提出应用该方法检测的不确定度评定结果。     

基于改进的 AlexNet 卷积神经网络的植物叶片识别

针对多类植物叶片识别准确率和计算效率低问题,通过残差连接卷积层,构建了一种基于残差连接的Alexnet卷积神经网络。对卷积层的输入数据进行批归一化,进而加速网络的收敛速度。利用两种不同的全局池化算法既能减少特征图数目又能提高算法识别植物叶片的准确性和计算效率。对于不同种类植物叶片,实验验证残差连接的Alexnet卷积神经网络能够进行高效识别。     

基于MATLAB图像处理的大豆颗粒检测方法研究

为解决大豆单株考种过程中人力计数准确率低和数粒仪等光电方法耗时长等问题,采用计算机视觉系统及MATLAB软件开发平台代替人工大豆单株考种进行自动检测的方法。该算法采用对大豆颗粒图像进行空间滤波去除噪声及“Otsu”方法对图像进行最佳全局阈值分割处理,在对图像处理的基础上完成对大豆颗粒个数、颗粒大小两项指标的测定。以六个大豆品种周黑豆、周青豆、周豆11、周豆18、周豆22和周豆23的籽粒为试验对象,探究大豆颗粒计数、大豆颗粒大小分级两项指标的确定。实验结果表明：该算法及程序准确有效,能准确计算大豆单株颗粒个数;该算法及程序判断出的各品种大豆颗粒平均面积大小与百粒重成正相关,且决定系数为0.9141,即可得该算法及程序可准确有效的判断大豆颗粒大小。总之,基于MTALAB图像处理大豆单株颗粒检测方法的研究可相对减轻人力劳动强度及人类视觉的不足,在提高工作效率和准确度等方面有重要意义。     

基于Memetic算法的两级车辆路径优化

针对传统两级车辆路径优化过程,存在的精度不高,收敛时间过长的问题,提出一种基于Q学习理论和差分进化的Memetic算法。首先,对两级车辆路径优化问题进行研究,利用最优分割法获得第一级配送方案,以此确定中转站配送数量,然后求解第二级多配送中心车辆路径问题配送方案,获得两级优化问题的总里程及总配送车辆数量;其次,针对第二级MDVRP配送方案求解,利用Q学习理论和差分进化算法,设计新的Memetic算法,来实现对多配送中心车辆路径问题配送方案的全局优化;最后,通过仿真验证了所提算法的有效性。     

Application of Engineering WorkStation in Analysis of Truck Crashworthiness

This paper presents the basic equations and algorithm of vehicle crashworthinessbriefly.Take a light-truck for example,some applied problems in ustng Engineering WorkStationto analysis truck crashworthiness are discussed.A installation method of contact surface is intro-duced,Finally,a nurnerical simulation result is presented.     

Design of Data Acquisition System for Vehicle Based on CAN Bus

To the question that a meter is correspond with a set of lead and a sensor,this paper presents a design of data acquisition system for vehicle based on CAN bus.In this way,the combinatorial instrument is only connected by a bus unit.Author introduces the data acquisition structure chart and the CAN interface,analyzes the software by program flow chart,and shows it's application for vehicle virtual instrument.A method of calculating vehicle speed,engine rotate speed and the course of development mileage are also given.     

A data selection method applied to on-line drift compensation for gas sensors

A new data culling and labeling method is proposed to avoid misleading outcomes caused by multi-state samples during drift compensation process. This method culls data by the curve slops of gas sensor array response and labels data by comparing input samples with the memories of pattern recognition algorithm to avoid occurrence of misleading results. Experiments show the method combined with on-line drift compensation algorithm can estimate sample-states automatically and increase the recognizing accuracy from 37.5% to 100%.     

Research of the Ignition Timing System for Compressed Natural Gas Vehicle

Compared to bi-fuel engine,it uses completely CNG(Compressed nature gas) to replace diesel which can save more oil fuel than bi-fuel engine that reffited diesel engine into CNG engine. A 4102 diesel engine is refitted into CNG engine and a mechanical ignition timing system is designed by the method of gear and belt. The principles and the construction of the system is introduced and the characteristics of the design is analyzed. The system performed well and had good liability when run in a platform. Compared with the previous one, it kept higher dynamic character and emitted lower. It is a cheap one and can be use to reform the diesel engines.     

Improved Vehicle Detection Algorithm Based on Edge Information

Collecting real-time traffic flow information is a foundational function in intelligent transportation systems. Video based traffic monitoring system has advantage of installation and maintenance, so it iswidely used for traffic monitoring on main road and crossroad. Shadows result from roadside building or trees are one of the factors that arise errors in video based vehicle detection. An improved method based on edge information is proposed for vehicle detection and shadow rejection. Finally vehicle counting is achieved based on the edge detection method.     

State of charge estimation of lithium iron phosphate batteriesbased on adaptive Kalman filters

The Kalman filter algorithm can be used to estimate the state of charge (SOC) of power batteries, however, it easily causes divergence due to uncertain of system noise and its estimation performance is affected by model. An adaptive Kalman filter algorithm is adopted to dynamically estimate SOC of lithium iron phosphate batteries for application in electric vehicles. At first, an equivalent circuit model, appropriate for SOC estimation is built after studying battery models. Then some charging and discharging experiments are carried out for parameter identification and the results are verified. At last, the adaptive Kalman filter algorithm is used on this model for on-line SOC estimation under unknown interfering noise. Simulation results show that adaptive Kalman filter method can correct SOC estimation error caused by tiny model error online, and the estimate accuracy is higher than Kalman filter method. Adaptive Kalman filter algorithm can also correct the initial error. Full-cycle test in electric vehicles proves that the algorithm is appropriate for SOC estimation of lithium iron phosphate battery.     

A new pattern recognition method of gas sensor array detection

BP neural network based gas sensor array detection pattern recognition has some disadvantages, such as slow convergence and local minimum problem. A modified immune neural network model which combines BP algorithm and immune algorithm is proposed to enhance global search capability and improve the performance of the neural network model. Orthogonal test is adopted to design the study samples of neural network. This ensures the accuracy of neural network while reducing the number of samples. The simulation results show that the proposed pattern recognition method solves the cross sensitivity of gas sensor effectively, overcomes the disadvantages of traditional BP neural network and improves the learning speed and detection accuracy.     

A novel shuffled frog leaping algorithm for ICPT power programming

A new mode of inductively coupled power transfer (ICPT) is presented to city electrization traffic vehicle power supply optimization. The power supply distribution plan and ICPT technology are investigated. To avoid the local optimal of shuffled frog leaping algorithm (SFLA),a novel algorithm based on mutative scale chaos search and SFLA is presented. It is applied to inductively coupled power transfer substation optimal planning. The advantages of global and local search strategies for SFLA are combined with the proposed algorithm. In order to implement local refined search to improve local chaotic search ability and to enhance the solution accuracy, mutative scale chaos search is introduced to the proposed algorithm. The minimum annual expense of the proposed algorithm is 2.39% less than that of SFLA, which shows its advantage.     

Double-Face Dynamic Balance Method of Spot Rotator without Removing the Test Weights

Site dynamic balance is a important element in installation and maintenance of heavy rotary mechanism. It's hard to discharge testing weights, and the remanent weights will effect the result of balance test. The paper presents a kind of dynamic balance algorithm which need not to discharge the test weights, basing on influence coefficient. The principle of the algorithm is to balance the sum of original unbalance weights and testing weights by the result balance weights. In the algorithm , the influence coefficient of last time can be used optionally for the same rotor. Then developing a dynamic balance system building on it. The site experimental results indicates that this algorithm has a high balance precision, predigests the steps and reduces the operation time.