基于CAN总线的柴油发动机参数自动监测系统

开发了一种CAN总线和SAE J1939协议的柴油发动机运行参数自动监测系统,设计了微控制器与CAN总线连接电路、上位机通信电路设计和电源电路,实现了发动机参数的实时采集和监控,提高了发动运行的安全性.     

电动公交客车CAN总线网络通信结构的设计

为了研究电动公交客车上CAN总线网络节点信息的实时性及可靠性问题,依据CAN总线网络通讯协议技术的特点,研究并设计了一种电动公交客车的CAN总线网络通讯结构,并给出了适用于电动公交客车的SAE J1939应用层协议及汽车CAN总线网络的硬件接口模块,软件模块采用了基于优先权竞争的模式,通过CAN总线网络和基于优先权模式的方法,实现了实时采集、分析、处理电动公交客车的各个数据节点的信息和数据.最后,在路况测试中通过对实际数据的采集,验证了电动公交客车CAN总线网络通讯结构的硬件、软件模块设计合理,具有实际的学术价值和应用前景.     

On the fatigue behaviour of quenched and tempered at 300 and 600 °C SAE 1045 steel in an environment of sugar cane juice

SAE 1045 steel is widely used for manufacturing shafts in the sugar cane mills of the sugar industry. These shafts are designed with an expectation of a long lifetime. However, fatigue failures occur frequently. The sugar cane juice processed in these mills has corrosive properties that can alter the fatigue life of these shafts. In this research, the fatigue strength of SAE 1045 steel between 1 × 10⁴ and 2 × 10⁵ cycles in air and in sugar cane juice, with two different microstructures (tempered martensite at 300 °C and tempered martensite at 600 °C), was determined in rotating bending. The microstructure of the materials was characterized using optical microscopy, and the fracture surfaces were characterized using scanning electron microscopy. The results show that the fatigue strength at 2 × 10⁵ cycles for the tempered condition at 600 °C decreases 7% because of the sugar cane juice effect, and for the tempered condition at 300 °C, the fatigue strength decreases 15%.     

热处理工艺对SAE4140钢板组织和性能的影响

通过光学显微镜和力学性能等测试手段,对比分析了正火+回火与淬火+回火热处理工艺下SAE4140钢板的组织及力学性能变化,为制定代替原调质工艺提供理论指导。结果表明,13mm厚SAE4140钢板在850℃正火,540℃～560℃区间进行回火得到的NT态钢板性能与QT态钢板相近,并且批量生产效果良好。     

SAE J1939协议开发及其在高压共轨系统中的应用

SAE J1939协议是中重型道路车辆上控制器局域网的通用标准,本文实现了SAE J1939协议中除了网络层以外的所有基本功能,并在基于Infineon C167平台上完成与高压共轨系统控制软件的集成,通过CANoe软件模拟测试和连接CAN总线汽车仪表实际测试表明,所开发的协议实现了所有预期功能。     

车载双路CAN总线冗余网关的设计

为了使现有车载网关的实时性、稳定性和可靠性得到进一步的提高,基于双核16位单片机MC9S12XDP512设计了车载双路CAN总线冗余网关方案.在设计中采用了双路CAN总线冗余备份方案,并且还采用了嵌入式系统设计的双核技术,开启了单片机内的协处理器XGATE来处理各种中断,使主处理器集中进行数据的处理工作.该设计方案简单易行、便于实现,且通用性强,也有利于开发和维护.     

一种基于BOA-SAE-EELM的光伏阵列故障诊断方法

光伏阵列非线性输出的特性以及最大功率点跟踪算法,会影响光伏阵列保护设备的工作.为了正确辨识光伏阵列的运行状态,本研究提出一种基于贝叶斯优化算法(BOA)、堆栈自动编码器(SAE)以及集成极限学习机(EELM)相结合的故障诊断方法.首先,将光伏阵列的时序波形进行标准化处理;接着,使用SAE对标准化后的时序波形进行特征自动...     

Fatigue assessment and fatigue life calculation of quenched and tempered SAE 4140 steel based on stress–strain hysteresis, temperature and electrical resistance measurements

In this paper, mechanical stress–strain-hysteresis, temperature and electrical resistance measurements are performed for the detailed characterization of the fatigue behaviour of quenched and tempered SAE 4140 steel used for many applications in the automotive industry. Stress-controlled load increase and constant amplitude tests (CATs) were carried out at ambient temperature on servo-hydraulic testing systems. The applied measurement methods depend on deformation-induced changes of the microstructure in the bulk material and represent the actual fatigue state. The plastic strain amplitude, the change in temperature and the change in electrical resistance can be equally used for an assessment of baseline fatigue properties in generalized cyclic deformation curves as well as in generalized Morrow and Coffin–Manson curves. On the basis of comprehensive experimental fatigue data, the physically based fatigue life calculation method ‘PHYBAL’ based on the generalized Basquin equation was developed. S–N (Woehler) curves calculated with ‘PHYBAL’ using data from only three fatigue tests agree very well with the conventionally determined ones.     

混合电动车能量回馈控制系统设计

制造高性能的混合动力电动车的关键是其各个子系统的协调工作,以及各个子系统之间检测参数的共享,因此对各个子系统之间通信的实时性和信息共享性具有较强的要求。本文主要研究基于CAN总线的混合制动能量回馈系统,采用SAE 1939协议,搭建了CAN总线整车控制网络,系统根据工况将总制动力矩按不同比例分配为能量回馈制动、机械制动和ABS制动,实现最优制动。     

栈式自编码的恶意代码分类算法研究

针对传统机器学习方法不能有效地提取恶意代码的潜在特征,提出了基于栈式自编码(Stacked Auto Encoder,SAE)的恶意代码分类算法。 其次,从大量训练样本中学习并提取恶意代码纹理图像特征、指令语句中的隐含特征;在此基础上,为提高特征选择对分类算法准确性的提高,将恶意代码纹理特征以及指令语句频度特征进行融合,训练栈式自编码器和softmax分类器。 实验结果表明：基于恶意代码纹理特征以及指令频度特征,利用栈式自编码分类算法对恶意代码具有较好的分类能力,其分类准确率高于传统浅层机器学习模型（随机森林,支持向量机）,相比随机森林的方法提高了2.474％ ,相比SVM的方法提高了1.235％。