Optimization on the Crosswind Stability of Trains Using Neural Network Surrogate Model

Under the influence of crosswinds,the running safety of trains will decrease sharply,so it is necessary to optimize the suspension parameters of trains.This paper studies the dynamic performance of high-speed trains under cross-wind conditions,and optimizes the running safety of train.A computational fluid dynamics simulation was used to determine the aerodynamic loads and moments experienced by a train.A series of dynamic models of a train,with different dynamic parameters were constructed,and analyzed,with safety metrics for these being determined.Finally,a surrogate model was built and an optimization algorithm was used upon this surrogate model,to find the mini-mum possible values for:derailment coefficient,vertical wheel-rail contact force,wheel load reduction ratio,wheel lateral force and overturning coefficient.There were 9 design variables,all associated with the dynamic parameters of the bogie.When the train was running with the speed of 350 km/h,under a crosswind speed of 15 m/s,the bench-mark dynamic model performed poorly.The derailment coefficient was 1.31.The vertical wheel-rail contact force was 133.30 kN.The wheel load reduction rate was 0.643.The wheel lateral force was 85.67 kN,and the overturning coef-ficient was 0.425.After optimization,under the same running conditions,the metrics of the train were 0.268,100.44 kN,0.474,34.36 kN,and 0.421,respectively.This paper show that by combining train aerodynamics,vehicle system dynamics and many-objective optimization theory,a train's stability can be more comprehensively analyzed,with more safety metrics being considered.     

基于近似模型的高速列车头型多目标优化设计

为改善高速列车气动性能,建立一套高效的多目标气动优化设计方法,对流线型头型进行多目标气动优化设计。建立高速列车流线型头型三维参数化模型,并提取5个优化设计变量;为减少优化设计时间,利用最优拉丁超立方设计方法在优化设计空间中进行均匀采样,利用计算流体力学方法获得对应于各个采样点的气动载荷,利用Kriging代理模型构建优化设计变量和气动载荷之间的近似模型;利用多体系统动力学方法计算气动载荷作用下的高速列车轮重减载率;以气动阻力和轮重减载率为优化目标,利用多目标遗传算法NSGA-II对高速列车流线型头型进行多目标优化。优化设计变量和优化目标均呈现收敛的趋势,采用Kriging近似模型优化计算的Pareto前沿与采用CFD（Computational fluid dynamics,CFD）优化计算的Pareto前沿较为接近。优化后高速列车的气动阻力最多可降低3.27%,轮重减载率最多可降低1.44%,气动阻力最优的头型与轮重减载率最优的头型的主要差异在于中部辅助控制线的变化,前者向内凹,后者则向外凸。     

基于转子端数据驱动LSTM-CNN模型的高速旋转系统运行状态识别方法

针对复杂结构高速转轴运行状态难以准确实时监测与识别的问题,提出了一种基于转子系统数据驱动的复合神经网络转轴工况识别方法。首先,提出了一种基于长短期记忆网络(Long short-term memory,LSTM)和卷积神经网络(Convolutional neural networks,CNN)的复合神经网络模型(LSTM-CNN)。然后,建立双盘转子动力学仿真模型,并利用Newmark-β法对转子系统进行数值求解,获得转子系统关键固定节点动力学响应特征;同时基于有限元仿真获得关键旋转节点的动力学响应特征,并将两类数据分别导入LSTM-CNN模型中进行工况识别,并对其准确率和效率进行比较分析。最后,设计搭建高速转子实验平台,获取转子端和固定端数据分别对模型进行训练与验证,比较不同模型对高速转轴运行状态的识别能力。仿真数据与实验验证分析结果均表明基于转子端数据驱动的LSTM-CNN模型识别比传统的基于固定端数据驱动的识别方法具有更优的识别精度和效率。     

基于伴随方法的高速列车头型气动优化

为改善高速列车明线运行时的气动性能,基于伴随方法和径向基函数网格变形技术,开展高速列车头型气动优化设计。采用径向基函数网格变形技术,避免列车头型优化过程中的网格重复生成,提高头型优化的效率。通过伴随方法求解目标函数对列车头型的敏感度,无须定义任何的头型设计变量,避免人为指定设计变量对优化结果的影响。将网格变形技术、伴随方法及计算流体动力学（Computational fluid dynamic,CFD）方法相结合,构建高速列车头型优化设计流程,选取整车气动阻力和尾车气动升力为优化目标,对高速列车头型进行多目标气动优化设计。结果表明：伴随方法可以有效地应用于高速列车的头型优化;优化后,在满足约束条件的情况下,列车的整车气动阻力减小2.83%,尾车气动升力减小25.86%;气动阻力减小主要位于头尾车流线型部位,中间车和头尾车车体气动阻力基本保持不变;尾车气动升力减小主要位于流线型部位,尾车车体向下的升力绝对值也有所减小。     

高速列车轴箱振动无线采集器

随着铁路事业的飞快发展,列车运行速度越来越快,其运行安全显得尤为重要。轴箱作为列车走行部的关键部件,其振动情况可以很好地反映出列车的运行安全状态,本文介绍以JN5139低功耗无线通信模块和C8051F021单片机为基础,用于采集高速列车轴箱振动信号无线采集器的设计。     

横风下高速列车流线型头型多目标气动优化设计

为改善高速列车的横风气动性能,建立高速列车流线型头型的多目标优化设计方法,以横风下高速列车的侧力和升力为优化目标,对高速列车流线型头型进行多目标自动优化设计。建立高速列车流线型头型的参数化模型,提取出5个优化设计变量,利用计算流体动力学方法进行高速列车流场计算,并结合多目标遗传算法,实现横风下高速列车流线型头型的自动寻优设计。通过相关性分析,得到影响侧力和升力的关键优化设计变量,并进一步研究关键优化设计变量和优化目标之间的非线性关系。经过多目标优化设计,获得一系列的Pareto最优头型,这些头型的横风气动性能均得到明显改善。同时为保证无风环境下高速列车的基本气动性能不发生恶化,最终筛选出8个Pareto最优头型。对于这8个Pareto最优头型,相对于原始头型来说,横风下的侧力最多可降低3.06%,横风下的升力最多可降低19.60%,无风时的气动阻力最多可降低4.51%,无风时的气动升力最多可降低9.68%。     

高速高精度数控进给驱动的机电联合系统仿真

结合C++语言、Matlab软件和ADAMS软件,从整体上设计了一种复杂机电系统仿真方案,建立了数控进给驱动系统的机电联合仿真平台。该仿真方案包括了复杂运动指令的生成、交流伺服控制和多体系统动力学。利用所建立的联合仿真平台对数控进给驱动动态特性进行了仿真分析,并与实验结果进行了对比,最后对两种典型的加减速指令方法进行了仿真比较。表明该仿真平台能够分析和评价高速高精度数控进给驱动的整体动态特性,为数控进给驱动的整体设计提供参考。     

基于SysML的模型驱动复杂产品设计的信息集成框架研究

针对如何为复杂机电产品建立不同层次、不同物理域的设计信息及其与仿真信息间的关联这一重要问题,以系统建模语言SysML为基础,提出了支持模型驱动多域复杂产品多层次设计与仿真信息集成框架;建立了基于SysML扩展的核心集成信息模型,以支持系统设计与仿真集成及不同层次设计过程的信息集成。以此为基础,重点研究了SysML和Simscape建模语言的元模型及其间的映射规则,以及基于三元图文法的系统层设计信息与仿真信息动态关联与集成的方法。最后给出了实例进行分析验证。     

基于SIMPACK仿真分析的高速列车蛇行失稳识别方法

高速列车的横向运动稳定性不仅会影响列车的运行品质,还影响车辆的运行安全.现有的高速列车失稳在线监测方法大多是对高速列车大幅蛇行失稳状态进行识别,然而高速列车的小幅蛇行失稳状态很难被准确有效地识别出来.为此,提出了一种基于信号分析的蛇行失稳识别方法,不但可以识别出大幅蛇行失稳,而且可以识别出小幅蛇行失稳.首先通过SIMP...     

基于接口匹配的机电系统概念设计功能求解

在机电一体化系统概念设计过程中,功能结构的生成和功能求解是交替进行、互为因果的关系。基于这一实际,提出了一种基于功能→效应→作用原理→结构方案映射的机电一体化系统概念设计反馈循环求解模型。分析了单一功能与机电系统功能的各自求解进程,研究了接口匹配及功能求解等反馈循环求解的关键实现技术,开发了一个机电系统概念设计自动化原型系统,并以电脑绣花机的概念设计为例进行了验证。     

An advisory system for the analysis and design of deformable beam-type multi-body systems

Multi-body systems can be used to model mechanisms, robots and many other mechanical assemblies. When these devices are subjected to high-speed and high accuracy requirements, their elastic behavior will merit thorough investigation. The finite element analysis and design of deformable multi-body systems is a very complex, iterative process requiring a high level of expertise and engineering intuition. This paper presents an advisory system developed to help a designer with the key parameters through the analysis, design, and validation processes. The related knowledge such as to determine the optimum parameters for mesh, time step, type of analysis, type of element, the numerical integration scheme and the corresponding parameters, and the design considerations such as material selection method, and geometric synthesis algorithm are also documented.     

Transforming Multidisciplinary Customer Requirements to Product Design Specifications

With the increasing of complexity of complex mechatronic products,it is necessary to involve multidisciplinary design teams,thus,the traditional customer requirements modeling for a single discipline team becomes difficult to be applied in a multidisciplinary team and project since team members with various disciplinary backgrounds may have different interpretations of the customers’requirements.A new synthesized multidisciplinary customer requirements modeling method is provided for obtaining and describing the common understanding of customer requirements(CRs)and more importantly transferring them into a detailed and accurate product design specifications(PDS)to interact with different team members effectively.A case study of designing a high speed train verifies the rationality and feasibility of the proposed multidisciplinary requirement modeling method for complex mechatronic product development.This proposed research offersthe instruction to realize the customer-driven personalized customization of complex mechatronic product.     

机电联合建模在直驱伺服系统设计中的应用

为了缩短直驱伺服系统设计周期,并保证所设计的系统的性能满足设计指标要求,提出了一种直驱伺服系统机电联合建模方法。以典型的直驱伺服系统为例,叙述了该建模方法的实现过程。建立了直驱伺服系统的动力学理论模型和基于Recurdyn和Matlab的机电联合仿真模型,在不同条件下对机电联合仿真模型进行了时域和频域仿真分析,并对仿真结果与系统实际测试结果进行了对比。结果表明：系统开环时域与频域仿真结果与实验结果基本吻合,幅频匹配度大于83%,相频匹配度大于73%,时域匹配度大于89%。得到的结果验证了提出方法的有效性和正确性,表明利用该方法可在设计过程中对设计方案进行性能预测,提高设计效率。     

复杂机电装备控制系统的三维图形仿真

提出一种基于三维CAD模型的机电系统仿真方法,以建立并验证控制系统的拓扑结构和控制逻辑。同时,通过基于三维模型的运动学仿真,可以发现复杂机电系统中的机械设计问题。仿真系统中编写的控制程序,只需要进行少量改动,就可以直接应用到实际设备中。运用该仿真系统可以显著缩短复杂机电装备的开发周期。     

高速列车驾驶界面设计中的照明眩光评估

高速列车驾驶环境中的照明眩光对界面设计有着十分重要的影响,如何在设计阶段对眩光进行有效的评估,是目前高速列车驾驶界面设计中面临的一个难题。针对高速列车驾驶界面照明环境复杂,眩光源的形状和边界难以判定,眩光计算参数值难以准确采集等问题,提出一种基于统一眩光评估(Unified glare rating,UGR)公式和小光源UGR修正公式的高速列车驾驶界面照明眩光评估模型,在利用视觉仿真方法获得包含驾驶员视觉仿真图像及其每一像素点光度学信息的基础上,通过对视觉仿真图像内的眩光源像素点进行判定、整合和筛除,获取高速列车驾驶界面照明眩光评估模型计算参数值,实现高速列车驾驶界面的眩光评估。采用被试主观评价试验对CRH3型车驾驶界面的12种照明方案进行眩光评估,并与提出的基于视觉仿真的照明眩光评估方法的计算结果进行对比分析,分析结果表明提出的方法与主观感受具有显著的线性关系。该方法可在设计阶段对高速列车驾驶环境照明眩光进行有效评估,为驾驶界面相关设计与优化提供指导。     

A new symbolic representation method to support conceptual design of mechatronic system

Regarding the typical mechatronic system that realizes controlled motion behaviour as the research object, the mechatronic system is composed of three subsystems, they are generalized executive mechanism subsystem, sensing and testing subsystem, and information processing and control subsystem. Based on the three subsystems, a new kind of symbolic representation method to represent a design scheme of mechatronic system is presented. This symbolic representation method includes graphical symbols, literal symbols and port information flows on the abstract layer of basic mechatronic function units in common use. Two applied instances are given. The method standardizes scheme representation of mechatronic system. The purpose is that the computer can identify and operate the standardized scheme representation. Furthermore, the method can be implemented in connection with related knowledge base to produce creative scheme. The symbolic representation method provides theoretical basis for computer aided conceptual design of mechatronic system.     

[设计与优化]市域铁路智慧站台门系统关键技术

针对市域铁路站台门面临的多种车型混跑、列车高速过站风压对站台门产生冲击等现状,提出了智慧站台门系统设计的关键技术及方案。基于升降式站台门技术实现了对多种车型车门位置的兼容,应用智能候车引导技术实现了乘客乘降出行的智能指引,通过智慧运维技术实现了设备的预防性维修和可靠性运营。同时,构建了车站区间气体流动的不可压缩三维不定常紊流模型,仿真分析了列车高速过站过程中气流流动特性,通过数值仿真求解了不同过站速度下站台门承受的风压冲击,并结合试验测试对其进行了验证。研究表明,当列车过站速度达到220 km/h时,距离站台边缘1.2 m处最大活塞风压为1913 Pa,小于设计许用压力2050 Pa。仿真分析及试验结果证明了站台门系统设计的安全可靠性。     

High-efficiency design optimization of a centrifugal pump

Design optimization of a backward-curved blades centrifugal pump with specific speed of 150 has been performed to improve hydraulic performance of the pump using surrogate modeling and three-dimensional steady Reynolds-averaged Navier-Stokes analysis. The shear stress transport model was used for the analysis of turbulence. Four geometric variables defining the blade hub inlet angle, hub contours, blade outlet angle, and blade angle profile of impeller were selected as design variables, and total efficiency of the pump at design flow rate was set as the objective function for the optimization. Thirty-six design points were chosen using the Latin hypercube sampling, and three different surrogate models were constructed using the objective function values calculated at these design points. The optimal point was searched from the constructed surrogate model by using sequential quadratic programming. The optimum designs of the centrifugal pump predicted by the surrogate models show considerable increases in efficiency compared to a reference design. Performance of the best optimum design was validated compared to experimental data for total efficiency and head.     

Die optimization design and experimental study of a large wallboard aluminum alloy profile used for high-speed train

The extrusion die plays a crucial role in the quality control of aluminum alloy profile production. But in practice, the design of extrusion die is mainly dependent on the experience and intuition of die designers; thus, many times of modifications and experiments should be undergone until an acceptable product is gained. In this paper, the extrusion process of a large wallboard aluminum alloy profile used for high-speed train was simulated by means of HyperXtrude software, and the flow behavior of material and deformation mechanism in the die cavity were investigated. With the simulation results of the initial die design scheme, a nonuniform velocity distribution in cross-section of the extrudate was observed. For optimizing the die design scheme, two optimal schemes (adoption of double-step welding chamber and introduction of baffle plate) were proposed. Through optimization, the velocity differences in the extrudate for optimal schemes are decreased from 39.9 to 12.2 and 10.8 mm/s, respectively. Thus, the uniformity of velocity distribution was improved in optimal schemes. The extrusion die design methods for large wallboard profiles were summarized and proposed, including the design methods of baffle plate and double-step welding chamber. Through trial production, a sound wallboard aluminum profile with good geometric shape and high dimensional accuracy was gained. Additionally, the mechanical properties of the extrudate were examined by means of experimental method. It is found that the test results stratified the practical engineering requirements.     

Calculation of design sensitivity for large-size transient dynamic problems using Krylov subspace-based model order reduction

Nowadays, transient dynamic responses of a large-size finite element (FE) model can be solved within a reasonable computation time owing to rapid improvement in both numerical schemes and computing resources. However, increasing demands for accurate simulation and complicated modeling have led to larger and more complex finite element models, which consequently result in considerably high computational cost. In addition, when structural optimizations include transient responses such as displacement, velocity, and acceleration, the optimizations often do not end within a reasonable process time because the large-size simulation must be repeated many times. In order to reduce the computational cost in this respect, model order reduction (MOR) for the original full-order model (FOM) can be used for the transient response simulation. In this paper, a transient dynamic response analysis using Krylov subspace-based MOR and its design sensitivity analysis with respect to sizing design variables is suggested as an approach to the handling of large-size finite element models. Large-size finite element models can incur the problem of a long computation time in gradient-based optimization iterations because of the need for repeated simulation of transient responses. In the suggested method, the reduced order models (ROMs) generated from the original FOMs using implicit moment-matching via the Arnoldi process are used to calculate the transient response and its design sensitivity. As a result, the speed of numerical computation for the transient response and its design sensitivity is maximized. Newmark’s time integration method is employed to calculate transient responses and their design sensitivities. In the case of the transient sensitivity analysis, we apply a temporal discretization scheme to the design sensitivity equation derived by directly differentiating the governing equation with respect to design variables. This methodology has been programmed on the MATLAB with the FE information extracted from the FE package ANSYS. Two application examples are provided to demonstrate the numerical accuracy and efficiency of the suggested approach. The relative errors of transient response and design sensitivity between the FOMs and ROMs are also compared according to the orders of the reduced model. Calculation of transient dynamic responses and their sensitivities using Krylov subspacebased MOR shows a sizeable reduction in computation time and a good agreement with those provided by the FOM.