Modeling retroreflectivity degradation of traffic signs using artificial neural networks

Traffic signs are vital for communicating guidance, rules, warning, and other highway agency information for safe and efficient navigation through transportation networks. Signs must be clearly detectable, readable, and understandable to fulfill their intended purpose. Poor sign visibility, particularly during nighttime, is the leading cause of fatalities worldwide. Sign retroreflectivity is one of the key measures to evaluate sign visibility conditions. It gradually deteriorates over time with sign aging, exposure, and other environmental conditions necessitating periodic sign maintenance or, ultimately, replacement when the sign retro values fall below the minimum prescribed standards. In literature, studies have mostly used traditional statistical regression models to model sign retroreflectivity as a function of available explanatory variables. Further, these studies have proposed separate retro degradation prediction models for different sign sheeting grades and colors that limit their applications for other scenarios. To fill the research gap, this study compared the performance of the linear regression method with three different architecture of the neural network namely, Feed-Forward Neural Network (FFNN), Cascade Forward Neuran Network (CFNN), and Elman neural networkNeural Network (ELMNN) for signs retro prediction with an aim to optimize sign maintenance and replacement activities and to enhance road safety. All the Neural Network models were employed with varying combinations of training algorithms, activation functions, and model parameters. Sign retro data for 539 in-service signs along selected sections of two expressways (M-1 and M-2) near the capital city of Islamabad in Pakistan were collected through portable handheld retroreflectometer GR3. Data on other sign attributes like sign ages (0, 2, 5, and 10 years), sign orientation, observation angle, sign sheeting brand, grade, and color were also acquired. Feature-based sensitivity analysis was conducted to identify the relative importance and ranking of input predictor variables. Model prediction results expressed in terms of various statistical evaluation metrics root mean square error (RMSE), mean absolute percent error (MAPE), RMSE-observation standard deviation satio (RSR), coefficient of determination (R²), Willmott's index of agreement (WIA), Nash-Sutcliffe efficiency (NSEC), and percent bias (PBIAS) showed that all the NN models outperformed the regression technique. Comparing the NN models, ELMNN architecture with 21 neurons in the hidden layer for ‘tansig’ activation function and ‘trainlm’ training algorithm yielded better retro-prediction performance. Feature sensitivity analysis revealed that variables sign age, sheeting brand, color, and observation angle were the most sensitive variables in predicting the retro output. Findings of this study can guide the transport agencies and decision-makers for effective policy implications and sign management practices.     

神经网络模型在高速公路软基沉降预测中的应用

借助人工神经网络模型 ,建立了可依据现场量测信息对软基路堤沉降量随时间而发展的过程进行动态预报的分析方法。其要点是 :建立公路软基沉降预测的神经网络结构 ,并将前期沉降观测值作为样本 ,通过神经网络结构的训练寻求沉降及其主要影响因素的内在关系 ,据以预测后期沉降量     

人工神经网络在ZL5OE装载机自动换档仿真中的应用

以装备有4D180型液力机械变速器的ZL50E装载机为例，通过人工神经网络（ANN）对其两参数换档规律进行系统建模和控制，并利用在换档实验中获得的数据进行验证性仿真，所得到的仿真档位与实验档位基本保持一致。表明人工神经网络档位控制系统可根据操作工况实现正确的变速箱档位控制，使自动变速系统具有了智能化特征，是一种有效的档位控制方法。     

A framework for short-term traffic flow forecasting using the combination of wavelet transformation and artificial neural networks

The main objective of this paper is to develop a framework for short-term traffic flow forecasting models with high accuracy. Due to flow oscillations, the real-time information presented to the drivers through variable message signs, etc., may not be valid by the time the driver reaches the location. On the other hand, not all compartments of the flow signal are of same importance in determining its future state. A model is developed to predict the value of traffic flow in near future (next 5–35?minutes) based on the combination of wavelet transformation and artificial neural networks. This model is called the hybrid WT-ANN. Wavelet transformation is set to denoise the flow signal, i.e., filtering the unimportant fluctuations of the flow signal. Unimportant fluctuations are those that have little or no effect on the future condition of the signal. The neural network is set and trained to use previous data for predicting future flow. To implement the system, traffic data of US-101 were used from Next Generation Simulation (NGSIM). Results show that removing the noises has improved the accuracy of the prediction to a great extent. The model was used to predict the flow in three different locations on the same highway and a different highway in a different country. The model rendered highly reliable predictions. The proposed model predicts the flow of next 5?min on the same location with 2.5% Mean Absolute Percentage Error (MAPE) and of next 35?min with less than 12% MAPE. It predicts the flow on downstream locations for next 5?min with less than 8% MAPE and for the different highway with 2.3% MAPE.     

基于BP神经网络轻型轿车排放模型的应用

本文利用BP神经网络理论,构造一个预测轻型轿车排放的BP神经网络模型,经验证,预测模型能较好地对一般轻型轿车排放结果进行定性预测,可以作为简易稳态工况法(ASM)尾气检测前的参考,对节约检测成本、提高一次检测通过率有着较高的实用价值;同时以南京市为例,研究了轻型汽油车行驶里程、使用年限等参数对排放的影响,为有针对性的维修治理提供可靠的依据。     

物元模型法在路面性能评价分析中的应用

采用物元分析方法,根据影响路面使用性能的一些主要因素,应用物元概念和关联函数,建立了路面使用性能评价的物元模型,对路面使用性能进行评价。并结合贵黄高速公路工程的一段实例进行分析和计算,结果与实际情况符合较好,说明该法在路面使用性能评价中是适用的。     

Practicability study on the suitability of artificial,neural networks for the approximation of unknown steering torques

For steer-by-wire systems, the steering feedback must be generated artificially due to the system characteristics. Classical control concepts require operating-point driven optimisations as well as increased calibration efforts in order to adequately simulate the steering torque in all driving states. Artificial neural networks (ANNs) are an innovative control concept; they are capable of learning arbitrary non-linear correlations without complex knowledge of physical dependencies. The present study investigates the suitability of neural networks for approximating unknown steering torques. To ensure robust processing of arbitrary data, network training with a sufficient volume of training data is required, that represents the relation between the input and target values in a wide range. The data were recorded in the course of various test drives. In this research, a variety of network topologies were trained, analysed and evaluated. Though the fundamental suitability of ANNs for the present control task was demonstrated.     

灰色经济计量学模型在交通量预测中的应用

交通量受到社会、经济、自然等多种因素的影响,作用机理繁复不明,且各地区交通调查资料不全给准确建模分析带来技术困难。鉴于灰色理论能分析缺少调查数据情况下复杂因素之间的相关性,线性回归模型可以较为明晰地对事物变化内在规律进行分析,本文尝试性地将农业领域的灰色经济计量学模型应用于交通量预测领域,基于河北省国道交通网年平均日交通量数据和社会经济统计资料建立交通量预测灰色经济计量学模型。研究表明,与其他预测模型相比,该模型具有更高的预测精度和理论合理性,并通过2007年实测数据验证了该模型的预测合理性和工程适用性。     

Black-box modelling of nonlinear railway vehicle dynamics for track geometry assessment using neural networks

ABSTRACT

The use of vehicle dynamics simulation for the track geometry assessment gives rise to new demands. In order to analyse the responses of the vehicles to the measured track geometry defects, the integration of the simulation process in the measurement chain of the track geometry recording car is envisaged. Fast and reliable simulation results are required. This work studies the use of black-box modelling approaches as an alternative to multi-body simulation. The performances of different linear and nonlinear black-box models for the simulation of the vertical and lateral bogie accelerations are compared. While linear transfer function models give good results for the simulation of the vertical responses, their use is not suitable for the highly nonlinear lateral vehicle dynamics. The lateral accelerations are best represented by recurrent neural networks. For the training and validation on high-speed lines using measured vehicle responses, the performance of the black-box simulation outperforms the multi-body simulation. Due to the larger variability of track design and track quality conditions on conventional lines, the model performance degrades and depends significantly on the analysed vehicle type and the track characteristics.     

Application of a thermodynamic model with a complex chemistry to a cycle resolved knock prediction on a spark ignition optical engine

A combination of experimental and numerical methodologies is proposed for the investigation of knocking in spark ignition engines to aid in better understanding the physical and chemical processes that occur and to exploit the capabilities of a developed computational tool. The latter consists of a thermo-fluid dynamics model, which is part of an advanced 1-D fluid dynamics code for the simulation of the entire engine, and a complex chemistry model, which can be embedded into the thermo-fluid dynamics model using the same integration algorithm for the conservation equations and the reacting species. Their mutual interaction in the energy balance will be considered. The experimental activity was carried out in the combustion chamber of an optically accessible, single-cylinder P.F.I. engine equipped with a commercial head. The experimental data consisted of optical measurements correlated to the combustion and auto-ignition processes within the cylinder. The optical measurements were based on 2-D digital imaging, UV visible natural emission spectroscopy and the chemiluminescence of radical species (OH and HCO). The engine parameters, the pressure signals of the related data and optical acquisition are compared on an individual cycle basis in the simulation by running the engine at a constant speed and varying the spark advance from normal combustion to heavy knock conditions.     

Evaluation of a brake assistance system (BAS) using an injury severity prediction model for pedestrians

Through the years, traffic engineers and researchers have developed a variety of countermeasures to enhance pedestrian safety. Pedestrian-vehicle collisions are regarded as the most serious type of accident since they incur high fatality rates. A fundamental concept in developing effective countermeasures is to analyze pedestrian-vehicle collisions scientifically, which can identify the causes of accidents and accident severity. The objective of this study was to investigate the pedestrian safety benefit of the brake assistance system (BAS) and a functional requirement associated with BAS, namely the time needed to safely detect a pedestrian ahead. An injury severity prediction model for pedestrians was developed to systematically evaluate the BAS in this study. Ordered multinomial logistic regression analysis was used to establish a statistical model capable of predicting pedestrian injury severity. In addition to vehicle characteristics, collision speed and pedestrian characteristics were used as independent predictor variables. The outcomes of this study would be useful in directing the development of safety policies and technologies associated with pedestrian safety.     

应用汽车行驶记录仪开创安全管理新模式

介绍了汽车行驶记录仪在国内外的应用、发展趋势及功能与作用，分析了我国道路运输安全生产管理落后的原因，探索应用汽车行驶记录仪开创安全管理新模式的途径。     

清包工模式在隧道工程成本管理中的应用

工程项目清包工,或称包清工,是在施工组织过程中将工程细目按照工、料、机分解细化,以工、料、机的形式体现每道工序的实际施工成本,并以实际施工成本实现外包的一种生产经营管理模式。文章结合山西省中条山隧道工程清包工运作模式的实践,阐述了清包工模式在隧道工程成本管理中的应用。     

同步碎石封层在减少半刚性路面非荷载型反射裂缝中的应用

着重介绍了半刚性基层沥青路面非荷载型反射裂缝的形成机理及同步碎石封层作为应力吸收层在防止、延缓反射裂缝形成中的作用。     

Design of ANFIS networks using hybrid genetic and SVD methods for modeling and prediction of rubber engine mount stiffness

Genetic Algorithm (GA) and Singular Value Decomposition (SVD) are deployed for optimal design of both the Gaussian membership functions of antecedents and the vector of linear coefficients of consequents, respectively, of ANFIS networks. These networks are used for stiffness modelling and prediction of rubber engine mounts. The aim of such modelling is to show how the stiffness of an engine mount changes with variations in geometric parameters. It is demonstrated that SVD can be optimally used to find the vector of linear coefficients of conclusion parts using ANFIS (Adaptive Neuro-Fuzzy Inference Systems) models. In addition, the Gaussian membership functions in premise parts can be determined using a GA. In this study, the stiffness training data of 36 different bush type engine mounts were obtained using the finite element analysis (FEA).     

Application of a reciprocity technique for measurement of acoustic transfer functions to the prediction of road vehicle pass-by noise

A technique based on the principle of acoustic reciprocity has been developed for measuring acoustic transfer functions of sound radiation from vibrating surfaces of the engine, power train, exhaust system and tires. In many realistic cases of sound radiation, reciprocal measurements of transfer functions are usually more convenient and mostly more accurate than the corresponding direct measurements. This paper explain the basic acoustic reciprocity and experimental setup and illustrate its benefits by application to measurements of transfer functions of sound radiation from the engine of a fully trimmed vehicle.     

Analysis process of a steering system using a concept model for idle vibration

This paper describes the development of an optimal design process for a steering column system and supporting system. A design guide is proposed at the initial concept stage of the development process to obtain sufficient stiffness of the steering system while reducing the idle vibration sensitivity of the system. Case studies on resonance isolation are summarized, where vibration modes among the systems are separated by applying a vibration mode map at the initial stage of the design process. This study also provides design guidelines for an optimal dynamic damper system using a CAE (computer aided engineering) analysis. The damper FE (finite element) model is added to the vehicle model to analyze the relation between the frequency and the sensitivity of the steering column system. This analysis methodology makes it possible to achieve target performance in the early design stage and reduction of damper tuning activity after the proto car test stage. Through the proposed steering column system development process, a lightweight vehicle with high stiffness is possible prior to the proto build stage. Furthermore, the improved process is expected to contribute to reducing the overall development period and the number of proto car tests necessary to achieve the desired steering system performance.     

Analysis of disc brake instability due to friction-induced vibration using a distributed parameter model

This paper deals with friction-induced vibration of a disc brake system with a constant friction coefficient. A linear, lumped, and distributed parameter model to represent the floating caliper disc brake system is proposed. The complex eigenvalues are used to investigate the dynamic stability, and, in order to verify simulations which are based on the theoretical model, an experimental modal test and dynamometer test are performed. The comparison of experimental and theoretical results shows good agreement, and the analysis indicates that modal coupling due to friction forces is responsible for disc brake squeal. Also, squeal type instability is investigated, using a parametric analysis. This indicates which parameters have influence on the propensity of brake squealing. This is helpful for validating the analysis model and establishing confidence in the experimental results of the modified system. These results may also be useful during system development or diagnostic analysis.     

Prediction of vibrating forces on meshing gears for a gear rattle using a new multi-body dynamic model

An efficient multibody dynamic model was developed to predict the vibrating transmitted gear forces of loaded and unloaded pairs of helical gears simultaneously at all speeds. The model can also calculate the bearing forces of a manual transmission that, in turn, may be converted to rattling noises. The bending of meshing gear teeth and torsional flexibility of transmission shafts were considered and embodied effectively in the multibody dynamic model by calculating the tooth bending stiffness and adding a torsion spring on a shaft section between two gears, respectively. The reactive forces on teeth and bearings were calculated and compared using three different models that were developed for this study — an equivalent model, a rigid-body model, and a frequency-based model. The equivalent model took only 58% computation time, compared to the frequency-based method, even though the two showed very similar results.