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.     

BP—GA算法在短时交通流预测中的应用研究

本文提出了一种基于BP神经网络的遗传算法,分别利用其局部和全局寻优能力强的特点综合为一种新的优化算法,并将改进的算法应用于交通流预测中。通过实例分析,可看到改进的模型在进行交通流预测时具有较好的预测效果。     

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。     

采用人工神经网络求解箱梁温度场算法研究

选用人工神经网络中的前向网络，应用反向传播算法，通过对箱梁温度场的研究，得到了统一的求解程序，解决了温度场实时求解问题。     

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.     

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.     

Modeling the accuracy of traffic crash prediction models

Crash forecasting enables safety planners to take appropriate actions before casualty or loss occurs. Identifying and analyzing the attributes influencing forecasting accuracy is of great importance in road crash forecasting. This study aims to model the forecasting accuracy of 31 provinces using their macroeconomic variables and road traffic indicators. Iran's road crashes throughout 2011–2018 are calibrated and cross-validated using the Holt-Winters (HW) forecasting method. The sensitivity of crash forecast reliability is studied by a regression model. The results suggested that the root mean square error (RMSE) of crash prediction increased among the provinces with higher and more variant average monthly crashes. On the contrary, the accuracy of crash prediction improved in provinces with higher per capita GDP, and higher traffic exposure. A 1% increase in crash variability, average historical crash count, GDP per capita, and traffic exposure, respectively, resulted in a 0.65%, 0.52%, −0.38%, and −0.13% change in the RMSE of forecasting. The addition of traffic exposure and macroeconomic factors significantly enhanced the model fit and improved the adjusted R-squared by 14% compared to the reduced model that only used the historical average and variability of crash count as the independent variables. The findings of this research suggest planners and policymakers should consider the notable influence of macroeconomic factors and traffic indicators on the crash forecasting accuracy.     

Modeling effects of driver safety attitudes on traffic violations in China using the theory of planned behavior

Traffic violations are recognized as one of the main causes of traffic accidents and have been found to be closely associated with driver attitudes toward traffic safety. In this study, a modified theory of planned behavior (TPB) was used to model the effects of driver safety attitudes on traffic violations, based on a questionnaire survey of 1505 drivers in China. In light of the strong correlations between the observed items, the items of the TPB components were grouped into several parcels, using an item-parceling method. Parcel-based structural equation modeling was then used to operationalize the modified TPB. The results indicate that the proposed model can accurately predict the occurrence of traffic violations based on the observed items related to driver traffic safety attitudes. It was found that driver attitudes, subjective norm, and perceived behavior control significantly affect traffic violations. For predicting traffic violations, driver attitudes toward traffic safety policies had the greatest influence, followed by driver attitudes toward risky driving behaviors and the attitudes of others toward risky driving behaviors. Finally, suggestions on traffic enforcement and education to reduce traffic violations are proposed based on the results.     

基于神经网络的汽车超载识别

载重不同的汽车以不同的速度驶过载重仪的受荷板时，对受荷板的冲击不同，因而安装在受荷板下的传感器的输出信号也不同。提取这一信号的四种特征值作为神经网络的输入值，对驶过载重仪的汽车是否超载进行识别。通过实验，验证了该方法的可行性。     

Plate scanning tools to obtain travel times in traffic networks

The management of vehicle travel times has been shown to be fundamental to traffic network analysis. To collect travel time measurement, some methods focus solely on isolated links or highway segments, and where two measurement points, at the beginning and at the end of a section, are deemed sufficient to evaluate users' travel time. However, in many cases, transport studies involve networks in which the problem is more complex. This article takes advantage of the plate scanning technique to propose an algorithm that minimizes the required number of registering devices and their location in order to identify vehicles candidates to compute the travel times of a given set of routes (or subroutes). The merits of the proposed method are explained using simple examples and are illustrated by its application to the real network of Ciudad Real.     

Capacity estimation of torque converters with piston holes using the response surface method and an artificial neural network

In new slim torque converters, lock-up clutches are used to provide high fuel efficiency at low speed. However, the slimness of the converters causes difficulty in heat dissipation, which may damage the friction material and shorten its life span. A cooling hole in the lock-up piston reduces the heat but also reduces the torque because oil flows through the hole due to the pressure difference between the two faces of the piston. In the early stages of the development of this type of torque converter, designers must consider the minimum flow rate required to cool the friction material and the minimum torque capacity required to transmit the engine torque. This research explored two methods of estimating these parameters. In the first method, an estimation equation was derived by combining the response surface method with physical properties such as the centrifugal force, a sudden expansion, a sudden contraction, and the steady flow energy equation. The second method involved the use of an artificial neural network. The feasibility of the estimates based on statistics and on the artificial neural network were confirmed in the design stage by comparing experimental and estimated data. An estimation program was created using the C#.Net language and has been used for actual torque converter designs by the Korea Powertrain Company.     

基于人工神经网络的柴油机故障诊断

故障诊断是计算机模式识别领域的一个活跃课题。文中提出了基于人工神经网络的柴油机故障诊断方法，设计了适合该诊断系统的BP网络结构，并给出了一种基于黄金分割法改进的BP算法，用来自适应调整网络学习速率。仿真结果表明：该算法具有很快的学习速度和较高的学习精度，完全适用于柴油机故障诊断系统。     

隧道锚喷支护设计的神经元网络方法

根据BP网络的基本原理，建立了隧道锚喷支护设计的神经网络模型，用“试错法”解决了中间层单元数的不确定性问题，通过对比分析，确定了网络的全局允许误差，解决了网络的训练时间问题，计算结果表明，该设计方法使得锚喷支护的定量化设计成为可能，产生的误差在实际工程中是可以接受的。     

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     

基于BP神经网络的黄土湿陷性预测研究

运用人工智能领域中的神经网络技术,提出了基于BP神经网络模型的黄土湿陷性等级的预测方法。用MATLAB7自带的神经网络工具箱编程来实现BP神经网络系统。并给出工程实例和程序,预测效果和准确度较好,说明利用BP神经网络预测黄土湿陷系数是可行的。     

基于BP人工神经网络的土基回弹模量反算

基于层状弹性理论构建路表弯沉值与结构层参数之间的数据库,并以该数据库建立BP神经网络模型,进行土基回弹模量的预测。理论与实测结果表明。所建立的土基回弹模量BP神经网络模型具有较好的预测精度,为准确、快速地评价土基的承载能力提供参考。     

基于神经网络的虚拟基准站自差分GPS定位的研究

提出了一种适合于铁路和公路固定线路的虚拟基准站自差分GPS定位的方法，讨论了建立动态虚拟基准站的方法及基于神经网络的虚拟基准站的结构，并对这一神经网络进行了训练。实验表明，系统的定位精度得到了提高，也有较强的动态跟踪能力。