Reconstruction of road defects and road roughness classification using Artificial Neural Networks simulation and vehicle dynamic responses: Application to experimental data

This paper reports the performance of an Artificial Neural Network based road condition monitoring methodology on measured data obtained from a Land Rover Defender 110 which was driven over discrete obstacles and Belgian paving. In a previous study it was demonstrated, using data calculated from a numerical model, that the neural network was able to reconstruct road profiles and their associated defects within good levels of fitting accuracy and correlation. A nonlinear autoregressive network with exogenous inputs was trained in a series–parallel framework. When compared to the parallel framework, the series–parallel framework offered the advantage of fast training but had a shortcoming in that it required feed-forward of true road profiles. In this study, the true profiles are not available and the test data are obtained from field measurements. Training data are numerically generated by making minor adjustments to the real measured profiles and applying them to a full vehicle model of the Land Rover. This is done to avoid using the same road profile and acceleration data for training and testing or validating the neural network. A static feed-forward neural network is trained and consequently tested on the real measured data. The results show very good correlations over both the discrete obstacles and the Belgian paving. The random nature of the Belgian paving necessitated correlations to be made using their displacement spectral densities as well as evaluations of RMS error percent values of the raw road profiles. The use of displacement spectral densities is considered to be of much more practical value than the road profiles since they can easily be interpreted into road roughness measures by plotting them over an internationally recognized standard roughness scale.     

A comparative study of destructive effects resulting from road profile acting on off-road towed vehicles

The more extreme conditions the vehicle is exposed to, the sooner it wears out and deteriorates. In order to determine the forces affecting the lifespan of vehicles we need to know the environmental conditions eliciting these forces.This research aims at elaborating and testing a method which can help to conduct a comparative analysis of forces acting on towed vehicles used in different terrain conditions. Excitation forces acting on a vehicle being towed across terrain cause vibrations which lead to wear and structural deterioration. The rate of deterioration depends on the activating forces resulting from the road profile geometry and the dynamic properties of the vehicle. A knowledge of the relationship between the towed vehicle and the terrain profile will enable the design of an artificial road profile for fatigue testing with which similar stresses arise as during normal use. With the developed comparative method, a connection can be established between stochastic road profiles and road profiles containing artificially built obstacles.     

Country road and field surface profiles acquisition,modelling and synthetic realisation for evaluating fatigue life of agricultural machinery

Fatigue life of agricultural machinery is strongly affected by the surfaces that these machines operate on. In the present paper a sensor-frame was developed to acquire road and field profiles in absolute geo-referenced coordinates. The sensor-frame was validated by measuring discrete trapezoidal bumps with known dimensions resulting in a root mean squared (RMS) error of 6–8 mm. Profiles were acquired from a country road and from a mowed grass field. Using the quarter-car vehicle model, the movement of an agricultural vehicle was simulated for various speeds. The resulted vertical loads were rainflow-counted and the accumulated fatigue pseudo damage was calculated using Palmgren–Miner linear rule. Based on the derived Power Spectrum Density (PSD), the profiles were classified according to ISO 8608 standard. Two methodologies were followed to model and create a number of synthetic realisations for each profile: Direct Spectrum Estimate (DSE) and ISO based modelling. Simulating the produced synthetic profiles with the quarter-car vehicle model, the corresponding pseudo damage was calculated. The accumulated damages from the DSE models were closer to the corresponding ones from the measured profiles. ISO based models could not model the profile irregularities, which proved to contribute the largest part of the accumulated fatigue damage.     

基于ED-LSTM的智能汽车神经网络横向动力学建模与控制

车辆动力学建模过程中通常会进行简化和假设, 导致模型在某些工况下无法准确反映车辆的实际动态特性, 影响控制精度甚至安全性. 鉴于此, 该文提出了一种基于数据驱动的非线性建模与控制方法, 建立了新型神经网络车辆横向动力学多步预测模型, 实现了智能汽车对参考轨迹的跟踪控制. 首先, 在分析车辆单轨模型并考虑轮胎非线性和纵向负载转移的基础上, 基于编码器?解码器结构设计神经网络横向动力学模型. 其中, 使用串行排列来扩展微分方程描述不完全的动力学信息, 隐藏层神经元学习车辆的高度非线性和强耦合特性, 进而提高模型全局计算精度. 利用所构建的数据集进行模型训练和测试, 结果表明, 相比于物理模型, 所提出的模型在不同路面附着系数条件下均具有更高的建模精度, 具有隐式预测路面摩擦条件能力. 其次, 利用提出的模型设计轨迹跟踪控制算法, 根据车辆稳态转向假设, 计算所需的前轮转向角和稳态质心侧偏角, 将稳态质心侧偏角纳入基于路径误差的转向反馈中, 实现参考轨迹跟踪控制. 最后, 使用CarSim/Simulink联合仿真及HIL实验测试进行不同工况试验的对比分析, 对所提出的基于神经网络模型的控制算法进行评价, 结果表明, 该模型能够实现智能汽车在高速下精确的跟踪控制效果, 并具有良好的横向稳定性.      

基于DRBF-EKF算法的车辆质心侧偏角与路面附着系数动态联合估计

车辆质心侧偏角和路面附着系数是实现车辆底盘智能化所需要的关键参数. 车辆质心侧偏角对于提高车辆安全性和操控性至关重要, 轮胎-路面附着系数决定轮胎力的峰值, 进而确定汽车的动力学稳定性边界. 本文针对四轮独立驱动电动汽车提出了一种基于惯性测量单元、轮毂电机内置转速/转角传感器的车辆质心侧偏角和路面附着系数动态联合估计方法. 对四轮独立驱动电动汽车进行车辆动力学分析, 结合Dugoff轮胎计算模型得到车辆质心侧偏角估计器; 利用机器学习中高维数据降维PCA多元分析方法, 提取主元特征参数, 建立路面附着系数估计器. 采用可自适应调节网络结构的双径向基神经网络和扩展卡尔曼滤波DRBF-EKF方法, 通过K-means算法改进RBF神经网络结构, 扩展卡尔曼滤波进行噪声滤波提高估计精度, 实现车辆质心侧偏角和路面附着系数的动态联合估计. 通过仿真和实车实验表明, 所设计的DRBF-EKF动态联合估计器实时性和估计精度均优于扩展卡尔曼滤波算法, 可以适应车辆行驶过程中路面附着特性与车速的变化, 表现出较强的鲁棒性; 与DRBF方法相比, 显著提高了估计精度; 并且分析了可以同时满足估计精度和实时性要求的最佳隐含层神经元个数.      

The influence of strong crosswinds on safety of different types of road vehicles

Strong crosswinds have a great influence on the safety of road vehicles. Different vehicle types may have different behavior under strong crosswinds, thereby leading to different dominant accident modes and accident risks. In order to compare the crosswind stability of road vehicles, a probabilistic method based on reliability analysis has been applied in this paper. The crosswind is simulated as a stochastic gust model with nonstationary wind turbulence. The vehicles are classified into several categories. For each vehicle type, a worst case vehicle model and the corresponding aerodynamic coefficients have been identified. Dominant accident modes and failure probabilities have been computed and are compared. The influence of road conditions (dry/wet) and wind directions on the crosswind stability has been taken investigated. The proposed model makes it possible to compare the effect of crosswind on different vehicle types based on a risk analysis.

     

An optimization method designed to improve 3-D vehicle comfort and road holding capability through the use of active and semi-active suspensions

The primary purpose of this paper is to analyze the effects of vibrations on the comfort and road holding capability of road vehicles as observed in the variation of different parameters such as suspension coefficients, road disturbances, and the seat position. This study required the development of a mathematical model to simulate the dynamic behavior of a 3-D vehicle. With this model, various types of non-linear suspensions such as active and semi-active suspensions may be investigated. The results obtained from the simulation of the 3-D vehicle demonstrate that the use of active and semi-active suspension models on road vehicles prove to be beneficial for comfort without unduly compromising road holding capability.     

Haul road defect identification using measured truck response

Current management techniques for the maintenance of mine haul roads, such as ad hoc blading, scheduled blading and even maintenance management systems, have shortcomings in complex mining environments. This paper investigates the possibility of using the response of haul trucks to aid the management of haul road maintenance. The question arises as to whether truck response data can be used to recognize road defects at specific locations, in terms of type and size. This is important since different defect types require different road maintenance strategies. A modeling methodology based on dynamic equilibrium of the unsprung mass of a haul truck is proposed and investigated.     

Autocorrelation model of road roughness

Road surface roughness is the excitation source for the dynamic response of a moving vehicle system. Driving comfort is indicated by either the driver absorbed power level or the vehicle vertical acceleration level. An autocorrelation function model for road roughness is proposed to specify the road surface random characteristics. Subsequently, the power spectral densities (PSDs) for both road roughness and vehicle response, the driver-absorbed power level, are formulated. A road quality index (RQI) in accordance with such energy considerations is defined to catalog the road grade. The laboratory test results show the applicability of the RQI method for road classification using the ISO criteria as a comparison check.     

Tyre rubber friction on a rough road

One of the most challenging aspects of vehicle dynamics is accurate modelling of the tyre-road interface. Forces between the tyre and road need to be accurately represented in simulation. This is challenging over rough roads since the friction changes along the road due to large surface asperities.The Heinrich/Klüppel friction coefficient estimation model has been implemented on smooth roads in the past. However, this study investigates the applicability of using this model over a rough but hard terrain, such as Belgian paving or cobblestones. The model is based on physical properties that can be determined mathematically or experimentally. The study includes detailed terrain topography and the difference between the top and bottom topography is used to determine the radially averaged PSD. Emphasis is placed on finding and implementing the flash temperature in a practical manner that could also be used in further studies.An experimental setup is built to validate the model. The experimental friction coefficient is compared to the friction coefficient calculated using the Heinrich/Klüppel model. The relative percentage error difference between experimental and friction model results is found to be less than 10% on a smooth concrete road and 20% on a rough road (concrete Belgian paving).     

Rural road characteristics and vehicle operating costs in developing countries

The primary phase of transportation at the smallholder level, from village to local market, is a particularly important aspect of increasing agricultural production in developing countries. The realistic prediction of vehicle operating costs on the (largely) unsurfaced roads in this sector is a useful input to development planning and a computer program has been developed to produce such predictions from first principles. When compared with survey results obtained by the Transport and Road Research Laboratory in Kenya, it is found that correlation is satisfactorily close. The program can also be used to predict the effects, on the operating costs of various vehicles, of changing road characteristics (gradient, curvature, roughness, rolling resistance and traction). It is found that rolling resistance and road roughness are the factors most likely to influence operating costs, due to their effects on vehicle speeds, fuel consumption and service/repair costs. Small, cheap machines are not necessarily superior to larger vehicles in terms of costs per tonne kilometre and fuel, particularly where the available load is sufficient to allow the larger vehicle to be utilized reasonably fully.     

Validating a GIS-based multi-criteria method for potential road identification

This paper investigated the validation of a multi-criteria method for identifying potential roads, and demonstrated the capability of analyzing GPS vehicle tracking data for identifying vehicle movement patterns and potential roads. The multi-criteria method was evaluated by comparing the predictions to the site visit results on 34 selected road segments meeting different criteria levels. Results show that locations meeting higher criteria levels have higher possibilities to be roads: an approximately 91% possibility of road existence for the locations meeting all five criteria; 55% for the locations meeting four criteria; and 14% for those meeting criteria level two or three. This approach provides an opportunity for land managers to update existing GIS roads map, or identify newly formed roads that may need either rehabilitation or inclusion into the roads maintenance program.     

Predicting the stability of low volume road embankments in contingency areas

The US Army often operates heavy vehicles in rural areas, operating on low-volume roads having limited load carrying capacity. Many of these roads, such as the ones on the outskirts of Baghdad, have been raised to prevent flooding from nearby canals or irrigated fields. Sections of the roads have collapsed under the weight of armored vehicles, resulting in injuries and even fatalities. For the selected area studied, 2½% of the low-volume road sections were determined to be high risk given typical wheel loads of heavy vehicles for soil strength conditions modeled as low. The goal of the research was to develop a method for rapidly evaluating the stability of a road based on soil conditions, wheel load, and the dimensions of a vehicle. A model for road stability was developed to assist in performing analysis of the canal roads outside of Baghdad. This analysis was then used to create maps and charts characterizing road stability to assist the drivers. The procedure described in this paper can be used to evaluate elevated roads in other parts of the world.     

Neural network solution to an inverse problem associated with the eigenvalues of the Stokes operator

A numerical method, based on the design of two artificial neural networks, is presented in order to approximate the viscosity and density features of fluids from the eigenvalues of the Stokes operator. The finite element method is used to solve the direct problem by training a first artificial neural network. A nonlinear map of eigenvalues of the Stokes operator as a function of the viscosity and density of the fluid under study is then obtained. This relationship is later inverted and refined by training a second artificial neural network, solving the aforementioned inverse problem. Numerical examples are presented in order to show the effectiveness and the limitations of this methodology.     

基于人工神经网络的湍流大涡模拟方法

大涡模拟方法(LES)是研究复杂湍流问题的重要工具,在航空航天、湍流燃烧、气动声学、大气边界层等众多工程领域中具有广泛的应用前景.大涡模拟方法采用粗网格计算大尺度上的湍流结构,并用亚格子(SGS)模型近似表达滤波尺度以下的流动结构对大尺度流场的作用.传统的亚格子模型由于只利用了单点流场信息和简单的函数关系,在先验验证中相对误差较大, 在后验验证中耗散过强. 近几年来,机器学习方法在湍流建模问题中得到了越来越多的应用.本文介绍了基于人工神经网络(ANN)的湍流亚格子模型的最新进展.详细地讨论了人工神经网络混合模型、空间人工神经网络模型和反卷积人工神经网络模型的构造方法.借助于人工神经网络强大的数据插值能力,新的亚格子模型的先验精度和后验精度均有显著提升. 在先验验证中,新模型所预测的亚格子应力的相关系数超过了0.99,在预测精度上远高于传统的大涡模拟模型. 在后验验证中,新模型对各类湍流统计量和瞬态流动结构的预测都优于隐式大涡模拟方法、动态Smagorinsky模型、动态混合模型等传统模型.因此, 人工神经网络方法在发展复杂湍流的先进大涡模拟模型中具有很大的潜力.      

Fuzzy Logic Control of Seat Vibrations of a Non-Linear Full Vehicle Model

In this paper, the dynamic behavior of a non-linear eight degrees of freedom vehicle model having active suspensions and a fuzzy logic (FL) controlled passenger seat is examined. The non-linearity occurs due to dry friction on the dampers. Three cases of control strategies are taken into account. In the first case, only the passenger seat is controlled. In the second case, only the vehicle body is controlled. In the third case, both the vehicle body and the passenger seat are fully controlled at the same time. The time responses of the non-linear vehicle model due to road disturbance and the frequency responses are obtained for each control strategy. At the end, the performances of these strategies are compared.     

Stochastic optimal active control of a half-car nonlinear suspension under random road excitation

The random response analysis and the stochastic optimal active control of a half-car model with nonlinear suspension stiffness and damping traversing a rough road are studied in this paper. The road roughness height is modeled as the output of a first-order linear filter to Gaussian white noise. Considering the hysteretic nonlinear stiffness and the square damping of the vehicle model, the response statistics of the nonlinear suspension with active control are obtained by using the equivalent linearization method. The performance indexes of the active suspension are evaluated and compared with those of the corresponding passive suspension. It is found that the nonlinear active suspension gives a better vehicle performances like ride comfort, suspension stroke and overall performance. Finally, the theoretical results are verified through Monte Carlo simulation.     

Ride comfort evaluation for road vehicle based on rigid-flexible coupling multibody dynamics

In the present research two different whole vehicle multibody models are established respectively, including rigid and rigid-flexible coupling multibody vehicle models. The former is all composed by rigid bodies while in the later model, the flexible rear suspension is built based on the finite element method (FEM) and mode superposition method, in which the deformations of the components are considered. The ride simulations with different speeds are carried out on a 3D digitalized road, and the weighted root mean square (RMS) of accelerations on the seat surface, backrest and at the feet are calculated. The comparison between the responses of the rigid and rigid-flexible coupling multibody models shows that the flexibility of the vehicle parts significantly affects the accelerations at each position, and it is necessary to take the flexibility effects into account for the assessment of ride comfort.     

异常天气条件下潮位过程神经网络补遗预测方法的研究

以异常天气条件下的实测潮位过程为研究对象,根据其为非平稳时间序列的特点,以人工神经网络BP算法作为预测工具,对潮位时间序列中缺失的数据进行补遗建立:差分方法人工神经网络模型;同一海域邻近潮汐测站潮位过程对应预测的去平均值法人工神经网络模型;对增减水现象潮汐过程预测的气象资料数据库人工神经网络模型。以实测资料验证上述方法的可行性,并取得了很好的预测结果。