Search results

To realize classification of different pavements, a road roughness acquisition system design and an improved restricted Boltzmann machine deep neural network algorithm based on Adaboost Backward Propagation algorithm for road roughness detection is presented in this paper. The developed measurement system, including hardware designs and algorithm for software, constitutes an independent system which is low-cost, convenient for installation and small.

The inputs of restricted Boltzmann machine deep neural network are the vehicle vertical acceleration power spectrum and the pitch acceleration power spectrum, which is calculated using ADAMS finite element software. Adaboost Backward Propagation algorithm is used in each restricted Boltzmann machine deep neural network classification model for fine-tuning given its performance of global searching. The algorithm is first applied to road spectrum detection and experiments indicate that the algorithm is suitable for detecting pavement roughness.

The detection rate of RBM deep neural network algorithm based on Adaboost Backward Propagation is up to 96 per cent, and the false positive rate is below 3.34 per cent. These indices are both better than the other supervised algorithms, which also performs better in extracting the intrinsic characteristics of data, and therefore improves the classification accuracy and classification quality. Additionally, the classification performance is optimized. The experimental results show that the algorithm can improve performance of restricted Boltzmann machine deep neural networks. The system can be used for detecting pavement roughness.

This paper presents an improved restricted Boltzmann machine deep neural network algorithm based on Adaboost Backward Propagation for identifying the road roughness. Through the restricted Boltzmann machine, it completes pre-training and initializing sample weights. The entire neural network is fine-tuned through the Adaboost Backward Propagation algorithm, verifying the validity of the algorithm on the MNIST data set. A quarter vehicle model is used as the foundation, and the vertical acceleration spectrum of the vehicle center of mass and pitch acceleration spectrum were obtained by simulation in ADAMS as the input samples. The experimental results show that the improved algorithm has better optimization ability, improves the detection rate and can detect the road roughness more effectively.

For the expected increase in the capacity of existing transportation systems and efficient energy utilisation, smart maintenance solutions that are supported by online and integrated condition monitoring systems are required. Industrial internet is one of the smart maintenance solutions which enables real-time acquisition and analysis of asset condition by linking intelligent devices with different stakeholders’ applications and databases. The purpose of this paper is to present some aspects of industrial internet application as required for integrating weather information and floating road condition data from vehicle mounted sensors to enhance effective and efficient winter maintenance.

The concept of real-time road condition assessment using in-vehicle sensors is demonstrated in a case study of a 3.5 km road section located in Northern Sweden. The main floating data sources were acceleration and position sensors from a smartphone positioned on the dash board of a truck. Features extracted from the acceleration signal were two road roughness estimations. To extract targeted information and knowledge, the floating data were further processed to produce time series data of the road condition using Kalman filtering. The time series data were thereafter combined with weather data to assess the condition of the road.

In the case study, examples of visualisation and analytics to support winter maintenance planning, execution and resource allocation were presented. Reasonable correlation was shown between estimated road roughness and annual road survey data to validate and prove the presented results wider applicability.

The paper describes a concept of floating data for an industrial internet application for efficient road maintenance. The resulting improvement in winter maintenance will promote dependable, safe and sustainable transportation of goods and people, especially in Northern Nordic region with harsh and sometimes unpredictable weather conditions.

The purpose of this paper is to investigate the optimum design of a quarter car passive suspension system using a particle swarm optimization algorithm in order to minimize the applied loads and vibrations.

The road excitation is assumed as zero-mean random field and modeled by single-sided power spectral density (PSD) based on international standard ISO 8608. The variance of sprung mass displacements and variance of dynamic applied load are evaluated by PSD functions and used as cost function for the optimization.

The advantages in using this methodology are emphasized by an example of the multi-objective optimization design of suspension parameters and the results are compared with values reported in the literature and other gradient based and heuristic algorithms. The paper shows that the algorithm effectively leads to reliable results for suspension parameters with low computational effort.

The procedure is applied to a quarter car passive suspension design.

The proposed procedure implies substantial time savings due to frequency domain analysis.

The paper proposes a procedure that allows complex optimization designs to be feasible and cost effective.

The design optimization is performed in the frequency domain taking into account standard defined road profiles PSD without the need to simulate in the time domain.

Realistic composite vehicles with 2, 3, 5 and 9 axles, consisting of a truck with one or two trailers, are addressed in this paper by computational models for vehicle–bridge interaction analysis.

The vehicle–bridge interaction (VBI) models are formed by sets of 2-D rigid blocks interconnected by mass, damping and stiffness elements to simulate their suspension system. The passage of the vehicles is performed at different speeds. Several rolling surface profiles are admitted, considering the maintenance grade of the pavement. The spectral density functions are generated from an experimental database to form the longitudinal surface irregularity profiles. A computational code written in Phyton based on the finite element method was developed considering the Euler–Bernoulli beam model.

Several models of composite heavy vehicles are presented as manufactured and currently travel on major roads. Dynamic amplification factors are presented for each type of composite vehicle.

The VBI models for compound heavy vehicles are 2-D.

This work contributes to improving the safety and lifetime of the bridges, as well as the stability and comfort of the vehicles when passing over a bridge.

The structural response of the bridge is affected by the type and size of the compound vehicles, their speed and the conservative grade of the pavement. Moreover, one axle produces vibrations that can be superposed by the vibrations of the other axles. This effect can generate not usual dynamic responses.

The purpose of this study is to propose a method for vulnerable pedestrians to visualize potential obstacles on sidewalks. In recent years, the number of vulnerable pedestrians has been increasing as Japanese society has aged. The number of wheelchair users is also expected to increase in the future. Currently, barrier-free maps and street-view applications can be used by wheelchair users to check possible routes and the surroundings of their destinations in advance. However, identifying physical barriers that pose a threat to vulnerable pedestrians en route is often difficult.

This study uses photogrammetry to create a digital twin of the three-dimensional (3D) geometry of the existing walking space by collecting photographic images taken on sidewalks. This approach allows for the creation of high-resolution digital elevation models of the entire physical sidewalk surface from which physical barriers such as local gradients and height differences can be detected by uniform image filtering. The method can be used with a Web-based data visualization tool in a geographical information system, permitting first-person views of the ground and accurate geolocation of the barriers on the map.

The findings of this study showed that capturing the road surface with a small wide-angle camera while walking is sufficient for recording subtle 3D undulations in the road surface. The method used for capturing data and the precision of the 3D restoration results are described.

The proposed approach demonstrates the significant benefits of creating a digital twin of walking space using photogrammetry as a cost-effective means of balancing the acquisition of 3D data that is sufficiently accurate to show the detailed geometric features needed to navigate a walking space safely. Further, the findings showed how information can be provided directly to users through two-dimensional (2D) and 3D Web-based visualizations.

The purpose of this paper is to present a practical and efficient iterative method for predicting vehicle-induced response of bridge.

The vehicle-bridge interaction (VBI) problem is generalized mathematically and a computational algorithm for VBI is proposed. This method rests on an iterative procedure, which utilizes the whole interaction process for iteration. By this means, vehicle and bridge become totally uncoupled and are only linked by the contact force history. This method provides flexibility to choose simplified or refined vehicle and bridge models for the VBI problem, as well as open options for different commercial FEM software without specialized codes.

The method is verified through two numerical examples. The first example uses a simple 1D beam bridge model, which illustrates the procedure of this method and demonstrates its fast convergence in several iterations. The second example employs a realistic full 3D finite element bridge model, which shows that the method easily connects complex FEM bridge models in ABAQUS with a calibrated vehicle model in Matlab. The dynamic response of the bridge is reliably calculated within only a few iterations.

The proposed iterative method separates vehicle and bridge into independent subsystems in the computational process, thus providing more flexibility to utilize commercial FEM softwares. Its efficiency is realized through choosing the whole interaction force process for iteration, which considerably reduces the iteration steps.

Develops a general five‐axle vehicle model to study the dynamic interactions between the moving mass and the bridge structural components. Two‐axle, three‐axle, or four‐axle sprung loads, and the limiting load conditions such as a moving constant force, a moving alternating force, a moving unsprung mass, and combinations thereof, can be treated as special cases of the more general case presented. Further, its integration with the versatile finite element modelling has enhanced the practical applicability of such a theoretical development. The physical characteristics of the bridge and the vehicle, such as the bridge geometry, mechanical properties, profile of the road surface, the vehicle parameters including the distance between axles, leaf springs suspension and the total weight, are considered explicitly in the present model. The dynamic equations of equilibrium in time are integrated using the Newmark integration scheme. Verifies the accuracy of the algorithm by comparing the numerical results obtained from the present formulation with the experimental results.

It is well known that public infrastructure, particularly the transportation infrastructure sector, is notorious for low efficiency, spending waste and corruption. Achieving the efficiency of public infrastructure investment is a crucial element to improve the current deteriorating condition of American transportation infrastructure system. The paper aims to discuss these issues.

This research utilizes an input-oriented, variable return to scale non-parametric data envelopment analysis to estimate the relative cost efficiency of highway infrastructure investment among the 48 American continental states from 1995 to 2009.

The empirical results reveal that there is a large efficiency variation among state highway infrastructure systems.

In addition, state governments on average reach 95.8 percent of the efficiency of their best practice peers in terms of providing quality highway infrastructure outcomes.

Suspension is a significantly important component for automotive and railway vehicles. Regenerative hydraulic-electric shock absorbers (RHSA) have been proposed for the purpose of attenuating vibration of vehicle suspension, and also recover kinetic energy originated from vehicle vibration that is conventionally dissipated by hydraulic dampers. To advance the technology, the paper aims to present an RHSA system for heavy-duty and railway vehicles and create a dynamic modelling to discuss on the development process of RHSA model.

First, the development of RHSA dynamic model can be resolved into three stage models (an ideal one, a second one with an added accumulator and a third one that considers both accumulator and system losses) to comprehensively evaluate the RHSA's characterisation. Second, a prototype is fabricated for testing and the results meet desired agreements between simulation and measurement. Finally, the study of key parameters is carried out to investigate the influences of hydraulic-cylinder size, hydraulic-motor displacement and accumulator pre-charged pressure on the RHSA system.

The findings of sensitivity analysis indicate that the component design can satisfy the damping characteristics and power performance required for heavy-duty vehicle, freight wagon and typical passenger train. The results also show that reducing the losses is highly beneficial for saving suspension energy, improving system reliability and increasing power-conversion efficiency.

The paper presents a more detailed method for the development and analysis of a RHSA. Compared with the typical shock absorbers, RHSA can also recover the vibration energy dissipated by suspension.

The purpose of this paper was to study the possibility of using smartphone roughness measurements for developing pavement roughness regression models as a function of pavement age, traffic loading and traffic volume variables. Also, the effects of patching and pavement distresses on pavement roughness were investigated. The work focused on establishing pavement roughness prediction models and applying these models to pavement management systems (PMS) to help decision-makers choose the best maintenance and rehabilitation (M&R) options by using cost-effective methods.

Signal processing techniques including filtering and processing techniques were used to obtain the International Roughness Index (IRI) from raw acceleration data collected from smartphone accelerometer sensors. The obtained IRI values were inputted as a dependent variable in analytical regression models as well as several independent variables with proper transformations.

According to the study results, several regression models were developed with a big variation in the coefficients of determination (R²). However, the best models included pavement age, accumulated traffic volume (∑TV) and construction quality factor (CQF) with R² equal to 0.63. It was also found that the effects of pavement distresses and patching was significant at a-level < 0.05. The patching effect on pavement roughness was found higher than the effect of other pavement distresses.

The presented results and methods in this paper could be used in the future predictions of pavement roughness and help the decision-makers to estimate M&R needs. The work focused on establishing IRI prediction models and applying these models to the PMS to help decision-makers choose the best M & R options.

To develop sound pavement roughness models, it is essential to collect roughness data using automated procedures. However, applying these procedures in developing countries faces several difficulties such as the high price and operation costs of roughness equipment and lack of technical experience. The advantage of using IRI values taken from smartphones is that the roughness evaluation survey may be expanded to cover the full road network at a cheaper cost than with automated instruments. Therefore, if the roughness survey covers more roads, the prediction model’s accuracy will be improved.