重型载货汽车气压制动系统危险状态识别

针对重型载货汽车因气压制动系统发生管路破裂、机械故障或热衰退导致制动效能下降且不易察觉从而引发严重交通事故的问题，提出基于主成分分析降维（PCA降维）和马尔可夫模型的气压制动系统危险状态识别方法。考虑到三轴载货汽车双回路制动系统的结构复杂性以及制动过程制动踏板动作、系统压力建立和实现车辆减速具有明显的时序性特点，首先采用PCA降维的方法对系统状态进行辨识；然后运用驾驶人制动意图与制动系统响应的双层隐形马尔可夫模型对系统状态进行识别。受驾驶人习惯影响制动踏板作用瞬间辨识度低，采用混合高斯聚类法提取不同制动意图时制动保持阶段数据建立制动意图识别模型和系统响应识别模型，通过二者匹配程度判定系统状态。最后，分别依据实车试验数据对模型进行离线训练和在线辨识验证。试验结果表明：系统正常状态下，基于PCA降维和马尔可夫模型相结合的识别方法能够准确、有效地识别制动系统状态；制动管路断开压力降低状态下，PCA降维方法能够及时有效识别其危险状态。     

Identification of nonlinear systems using modified particle swarm optimisation: a hydraulic suspension system

This paper presents a novel modified particle swarm optimisation (MPSO) algorithm to identify nonlinear systems. The case of study is a hydraulic suspension system with a complicated nonlinear model. One of the main goals of system identification is to design a model-based controller such as a nonlinear controller using the feedback linearisation. Once the model is identified, the found parameters may be used to design or tune the controller. We introduce a novel mutation mechanism to enhance the global search ability and increase the convergence speed. The MPSO is used to find the optimum values of parameters by minimising the fitness function. The performance of MPSO is compared with genetic algorithm and alternative particle swarm optimisation algorithms in parameter identification. The presented comparisons confirm the superiority of MPSO algorithm in terms of the convergence speed and the accuracy without the premature convergence problem. Furthermore, MPSO is improved to detect any changes of system parameters, which can be used for designing an adaptive controller. Simulation results show the success of the proposed algorithm in tracking time-varying parameters.     

基于深度卷积神经网络的钢材微观组织分类识别

通过引入多种深度卷积神经网络及分类器构建机器学习模型,对钢材金相图数据集进行学习,研究了一种能够准确、高效识别钢材微观组织的方法。研究结果表明,文章中所涉及的3种深度卷积神经网络在钢材微观组织的分类识别上均表现出优异性能,其中Inception-V3表现尤为突出,其与人工神经网络分类器组合而成的机器学习模型的分类精度可达99.60%。     

动荷载作用下钢结构涂装的累积损伤机理与量化模型

为研究动荷载作用下公路钢桥涂装层与基体间的协同变形和破坏机制,开发了钢结构涂装层试件的动荷载试验系统,研究了疲劳荷载作用下涂层的破坏模式、附着力、弹性厚度、应变等随循环加载次数的发展规律。结合涂层破坏模式和发展规律,构建了涂层疲劳累积损伤度的计算模型,提出了基于损伤度的涂层破坏分级方法,并结合试验结果进行了验证。结果表明:疲劳荷载将引起涂层的附着力下降、弹性厚度降低和应变松弛,进而导致涂层出现附着破坏、内聚破坏及其组合。涂层附着损伤度是涂层损伤的主要因素,且随加载次数持续增大,当加载次数较大时内聚损伤贡献突出。试验涂装体系在22万次应力循环后附着损伤度最大为0.34,内聚损伤度最大为0.27,总损伤度达0.61,属于严重损伤。提出的损伤度模型及破坏分级方法与试验规律吻合良好,可应用于公路钢桥涂装层受动荷载作用下的寿命预测。     

具有无序排列管片环结构的地铁盾构隧道数字模型智能重建北大核心CSCD

运营地铁隧道的管理、健康监测及维护正逐渐趋向于数字化、智能化;但常因地铁盾构隧道管理和检测单位缺少隧道数字模型,限制了地铁隧道智能维护和管理系统的应用和发展。文章针对地铁盾构隧道中无序排列的管片环结构,提出了一种基于深度学习和机器视觉的地铁盾构隧道数字模型智能重建方法,利用检测车获取的隧道衬砌内表面高清图片,对管片特征物(螺栓孔)进行智能识别与自动分类,再根据螺栓孔群的分布特点自动推断隧道管片环的排版规律,从而结合隧道实际线路实现隧道数字模型快速重建。某地铁隧道的实例应用结果表明,该方法适用于管片无规律性错缝拼装的情况,能以100%的准确率实现地铁盾构隧道数字模型的智能重建。     

Low-cycle fatigue assessment of offshore mooring chains under service loading

The integrity of mooring chains is essential to the safety of a range of offshore platforms. However, mooring line failures are occurring earlier than their design lives, with a high number of these failures occurring due to fatigue. Early in the fatigue life of the component fatigue initiation processes occur, where the fatigue hotspot is sensitive to the mean load and there is plastic strain accumulation from the multiaxial stress-strain responses of the material, leading to cyclic plastic damage accumulation. The traditional SN approach suggested by mooring standards does not consider these effects, and it is proposed that this lack of consideration under low-cycle fatigue conditions is the reason for the current non-conservative fatigue assessments of mooring chains. This paper aims to develop a fatigue approach based on a critical plane multiaxial fatigue criterion for mooring chains that can consider the damage-induced by the cyclic plasticity and the mean load effect, to investigate the importance of incorporating low-cycle fatigue into the mooring chain life prediction. To develop the critical plane approach, the multiaxial stress-strain states are extracted for the critical plane at the fatigue hotspot from a finite element model of a mooring chain. This is then correlated with a fatigue life prediction provided by conventional fatigue design data. It uses a simulation of an FPSO as a case study to demonstrate the importance of low cycle fatigue, which shows that the mean load effect is significant in reducing the fatigue life for mooring chain applications, while the effect of fatigue damage-induced cyclic plasticity is limited. The fatigue damage accumulation predicted by the critical plane approach is significantly higher than that of the traditional SN approach and should be accounted for in mooring line design.     

基于弹塑性分析的沥青面层破坏机理探究

采用数值仿真技术,利用美国宇航局大型数值模拟有限元软件MSC-NASTRAN,对半刚性基层沥青路面在汽车荷载下沥青面层结构自身的弹塑性响应状况进行了分析研究,对路面面层破坏机理提出了一些参考性意见。     

论桥下净空及梁板损坏的养护治理

针对高速公路桥下净空高度对梁板、地方车辆通行的影响,提出具体的养护措施,可供相关工程参考与借鉴。     

Time domain approach for coupled cross-flow and in-line VIV induced fatigue damage of steel catenary riser at touchdown zone

Existing VIV prediction approaches for steel catenary riser (SCR) typically employ truncation model without considering the interaction between the SCR and soil, and only allow for cross-flow (CF) VIV. In this study, a time domain approach accounting for the SCR-soil interaction is proposed to predict the CF and in-line (IL) VIV induced fatigue damage of a SCR at touchdown zone (TDZ). The hydrodynamic force resulting from the vortex shedding is modeled using the forced oscillation test data of a rigid cylinder and an empirical damping model, which are defined as functions of the non-dimensional dominant frequency and amplitude of the SCR response. Due to the coupling effect, the IL VIV force is magnified based on the CF VIV amplitude. By combining a linear hysteretic interaction model with a trench shape model, some particular phenomena during the vertical SCR-soil interaction are captured and qualitatively discussed, while for the horizontal direction, the seabed is simplified as nonlinear spring model. Based on these models, parametric studies are conducted to broaden the understanding of the sensitivity of VIV induced fatigue damage to the seabed characteristic. The results indicate trench depth, vertical and lateral stiffness, and clay suction are significantly affect the VIV induced maximum fatigue damage at TDZ.     

公路桥面铺装早期破坏原因分析及治理方法研究

鉴于重型卡车的增多对公路桥面造成了较大的伤害,通过分析其破坏原因,并提出有效措施治理,从而避免桥面破坏的加剧.