Shifting force control of an AMT heavy-duty truck based on manual shift test

Taking a heavy-duty truck as a research platform, the changing characteristics of shifting force, shift time, and slipping work are obtained through theoretical analysis and manual shift test of a real vehicle. Based on the analysis of the test results, a gear-shifting control strategy of the hydraulic automated shift control system is designed and experimentally verified on the bench. By optimizing the control parameters of high-speed switching valves, a control strategy and parameters are obtained, which can meet the requirements of dynamic performance and reliability.     

基于SDG深层知识模型的电站热力系统故障诊断方法

鉴于符号有向图(SignedDirectedGraph,SDG)深层知识模型的推理方法是一种完备的揭示系统故障的有效方法,提出将基于SDG的方法应用于电站热力系统的故障诊断中。应用该方法首先建立了除氧器系统的SDG模型,然后根据各个故障根源得出系统的子SDG模型,最后根据这些子图导出除氧器的故障诊断规则库。诊断时,通过将系统变量的定量值转换为定性值,将实际故障工况与所建立的故障规则进行比较,得到故障源的定性诊断结果。案例研究表明,该方法具有较好的解释性和诊断的快速性,且能有效解决仿真培训过程中误操作自诊断问题。     

车辆换档质量概念的完善与评价

研究了换档质量对车辆各部分性能的影响,给出了相应的评价指标。基于支持向量机的理论和技术,构建了换档质量评价系统。同时结合试验对装载自动机械式变速器的车辆进行分析,提出了新的、更加完整的换档质量评价概念,从而扩宽了传统换档质量评价的研究范围。试验分析表明,所建立的换档评价系统与传统评价方法相比,能够更加全面地表征换档质量对车辆性能的影响。     

Design of hydraulic shift mechanism for AMT vehicles based on the collaborative optimization method

Based on multidisciplinary design optimization (MDO), a new design method is put forward for hydraulic shift mechanism of heavy-duty vehicle automated manual transmission (AMT). Taking a shift cylinder for example, the collaborative optimization (CO) method for the design problem of a cylinder is devided into one system level design optimization problem and three subsystem level design optimization problems. The system level is an economic model and the subsystem level is mechanics, kinetics, and a reliability model. Application of the multidisciplinary design optimization software iSIGHT modeling and solving, optimal solution of the shifting cylinder CO model is obtained. According to the optimal solution, oil cylinders are machined out and installed on the gearbox of an AMT system for the bench cycle shift test. The results show that the output force and action speed of the optimized mechanism can meet requirements very well. In addition, the optimized mechanism has a better performance compared to the structure of the traditional design method, which indicates that the CO method can optimize the design of hydraulic transmission.     

Development of AMT Fault Diagnosis Technique Based on KWP2000

In order to make automatic mechanical transmission (AMT) capable of performing fault self-diagnoses and adaptive to standard communication interface,through technical analysis and intensive study concerning on-board diagnostic protocols now widely applied in Europe and America,KWP2000 on CAN is accepted as a technological path.An AMT fault communication system using hardware-in-the-loop simulation by dSPACE is developed,and communications compatible with ISO 15031-6 is realized on this module.Moreover,a han...     

基于变精度粗糙集的齿轮故障诊断

提出一种基于变精度粗糙集的齿轮故障诊断模型。首先用自组织特征映射神经网络进行数据的离散化;再由变精度近似依赖度进行属性约简;然后生成故障诊断规则。给出一个齿轮的故障诊断的实例,并与粗糙集的故障诊断模型进行比较。结果表明基于变精度粗糙集方法降低了决策规则的复杂度及规则数量,且提高了故障识别率。     

电动车辆AMT换挡过程中驱动电机控制策略

结合电动车辆的结构形式及其工作原理,研究了适用于电动车辆AMT(automated mechanical transmission)换挡过程的驱动电机控制策略,实现了AMT正常换挡.分析了制动状态下电机回馈制动力矩对AMT换挡的影响,提出了制动状态下AMT换挡时驱动电机控制策略.在纯电动环卫车上进行实车调试,结果表明,该控制策略可行,整个换挡时间约为1 s.     

基于SDG的集群打印系统故障智能诊断研究

随着网络购物的发展, 订单打印需求增大, 集群打印系统能够有效地提高效率。但集群系统需要较高的鲁棒性和可靠性, 因此订单监控和处理打印设备故障成为集群打印系统的核心问题。通过将具有实时监控节点数据和揭示故障传播路径特点的符号有向图(Signed Directed Graph, SDG)技术应用到集群打印系统, 建立了集群打印系统故障诊断推理规则, 并形成“If-Then”形式的诊断规则库。此外, 构建了订单全生命追踪模型, 结合诊断规则库对故障任务进行识别和管理, 实现了集群打印系统的故障任务转移和自恢复。     

Fault diagnosis of power-shift steering transmission based on multiple outputs least squares support vector regression

A method of multiple outputs least squares support vector regression (LS-SVR) was developed and described in detail, with the radial basis function (RBF) as the kernel function. The method was applied to predict the future state of the power-shift steering transmission (PSST). A prediction model of PSST was gotten with multiple outputs LS-SVR. The model performance was greatly influenced by the penalty parameter γ and kernel parameterσ2 which were optimized using cross validation method. The training and prediction of the model were done with spectrometric oil analysis data. The predictive and actual values were compared and a fault in the second PSST was found. The research proved that this method had good accuracy in PSST fault prediction, and any possible problem in PSST could be found through a comparative analysis.     

基于关联图和层次分析法的业务过程分析

通过分析面向中小企业的业务过程管理技术的特点,提出了基于关联图和层次分析法的业务过程分析技术.采用关联图表达业务过程的问题/失效模式及其原因之间的复杂关系,然后将关联图转换为递阶层次结构,并利用层次分析法定量计算各根本原因对问题的影响程度.通过对某企业制造过程管理的案例研究,证明了提出的技术满足中小企业对业务过程管理技术的要求.研究开发了一套简单易用的支撑软件系统,进一步降低了该方法对实施人员的专业知识要求,提高了方法的实用性.     

Fault diagnosis and process monitoring using a statistical pattern framework based on a self-organizing map

A multivariate method for fault diagnosis and process monitoring is proposed. This technique is based on a statistical pattern(SP) framework integrated with a self-organizing map(SOM). An SP-based SOM is used as a classifier to distinguish various states on the output map, which can visually monitor abnormal states. A case study of the Tennessee Eastman(TE) process is presented to demonstrate the fault diagnosis and process monitoring performance of the proposed method. Results show that the SP-based SOM method is a visual tool for real-time monitoring and fault diagnosis that can be used in complex chemical processes.Compared with other SOM-based methods, the proposed method can more efficiently monitor and diagnose faults.     

基于贝叶斯网络的海洋工程装备故障诊断模型

针对海洋工程装备结构工艺复杂、质量问题难以追溯的现状,构造了以工艺活动为中心的海洋工程装备贝叶斯网络故障诊断模型。该模型通过对海洋工程装备建造全过程的工艺进行结构和参数学习,结合专家意见构建贝叶斯网络、网络拓扑结构实现故障问题的智能推理诊断,以达到为实现质量追溯系统提供理论依据、提高企业质量管理水平的目的。最后,通过分析海洋工程装备平台建造中典型的焊接工艺贝叶斯网络,说明了贝叶斯网络在海洋工程装备领域的应用及其应用效果。     

Slow driving control of tracked vehicles with automated mechanical transmission based on fuzzy logic

In order to move tracked vehicles at an extremely slow speed with automated mechanical transmission (AMT), slow driving function was added in the original system. The principle and requirement of slow driving function were analyzed. Based on analysis of slow driving characteristic, identification of slow driving condition and fuzzy control algorithm, a control strategy of the clutch was designed. In order to realize slow driving, the clutch was controlled in a slipping mode as manual driving. The vehicle speed was increased to a required speed and kept in a small range by engaging or disengaging the clutch to the approximate half engagement point. Based on the control strategy, a control software was designed and tested on a tracked vehicle with AMT. The test results show that the control of the clutch with the slow driving function was smoother than that with original system and the vehicle speed was slower and steadier.     

基于有源自回归模型与模糊C-均值聚类的挖掘机液压系统故障诊断

为了提高挖掘机的可靠性水平和智能化程度,提出了基于有源自回归(ARX)模型与模糊C-均值(FCM)聚类的挖掘机液压系统故障诊断方法。该方法将故障诊断分成故障特征提取和故障分类两个部分。在故障特征提取中,针对已知故障和测试故障分别建立ARX模型,提取ARX模型的自回归系数作为故障特征。在故障分类中,以FCM聚类作为故障分类器,将测试故障归入已知故障的某个分类中,判断系统的故障类型。仿真和实验结果表明,ARX模型与FCM聚类相结合的故障诊断方法能有效地应用于挖掘机液压系统。     

基于最小熵解卷积与稀疏分解的滚动轴承微弱故障特征提取

针对滚动轴承早期故障难以提取和最大相关峭度解卷积（maxim correlated kurtosis deconvolution,MCKD）降噪效果受滤波器长度L的影响,提出了基于互补集合经验模态分解（complementary ensemble empirical mode decomposition,CEEMD）和自适应最大相关峭度解卷积相结合的故障特征提取方法（CEEMD-AMCKD）.首先,利用CEEMD将信号分解得到一组固有模态分量,利用峭度值筛选出冲击成分明显的分量;然后,以排列熵值为标准,运用步长搜寻法确定最佳的MCKD滤波器长度,对前面筛选出的分量进行降噪处理;最后,将降噪后的分量及其他分量进行信号重构并根据包络功率谱提取故障特征频率.通过仿真和试验验证了该方法的有效性.

     

基于结合能量模型的往复泵泵阀故障诊断研究

基于生物免疫系统抗原与抗体互识别的结合能量模型,结合矩阵的奇异值分解,研究了适于三缸往复泵泵阀故障诊断的新方法．通过对三缸往复泵泵阀实际故障的诊断分析,表明基于结合能量的故障诊断方法具有较强的容错性和鲁棒性,并具有可视化及可解释性好等特点。     

基于HHT/PNN的故障信息融合诊断方法

为提高动态随机故障诊断能力,提出了基于HHT/PNN的故障信息融合诊断方法.利用HHT提取信号的瞬时频率和瞬时幅值特征,采用过程神经元网络实现对时域幅值、瞬时频率和瞬时幅值3种故障特征的融合诊断.对基于HHT/PNN和基于神经网络的2种故障诊断方法进行了比较.仿真结果表明:对于动态随机故障,基于HHT/PNN的故障信息融合诊断方法比基于神经网络的故障诊断方法的故障诊断准确度高.     

Dirichlet过程混合模型的聚类算法

有限混合模型进行高维数据聚类分析时需预先估计聚类个数,因而聚类的准确性和泛化性受到影响.通过建立Dirichlet过程无限混合模型对高维数据开展聚类分析,采用Dirichlet过程的Urn模型分析出模型中各参数的后验分布,利用Gibbs采样MCMC方法估计出模型中各参数及数据中潜在的聚类数.在五维的仿真数据集和IRIS测试数据集上的聚类结果表明:经过200次Gibbs采样MCMC过程,该算法能够正确地估计出数据中潜在的聚类数.单次Gibbs采样MCMC过程的平均占用时间分别为0.185 0s和0.145 5s,其时间复杂度和数据的样本个数N有关,为O(N).     

改进PSO-BPNN的电力变压器故障诊断与模式识别

为了优化反向传播网络相关学习参数,提出一种粒子群优化辅助BP神经网络(BPNN)的新方法.以变压器油中气体体积分数百分比构造故障特征,将BP网络的初始权值和阈值进行实数编码,以对应PSO中的粒子,实现BP网络的离线训练与在线分析,对变压器故障模式做出判断.结果表明,该算法更合理地更新了粒子的位置和速度,最优地设置了全局极值,有效克服了粒子的早熟收敛,获得的故障诊断准确率高达91%,并大大提升了BP网络的收敛速度.该算法为此类设计提供了有效的模型参考.     

基于粒子群-小波神经网络的模拟电路故障诊断

针对传统小波神经网络技术在模拟电路故障应用中存在的问题,提出了一种基于粒子群-小波神经网络的模拟电路故障诊断方法.利用该方法对滤波电路进行了故障检测,结果表明,该方法优于传统的小波神经网络方法.