Artificial neural networks–based backcalculation of the structural properties of a typical flexible pavement

Pavement evaluation is one of the foremost phases in all pavement engineering activities. In the backcalculation process, the researcher or the engineer varies the structural properties of the layers until the theoretical (calculated) deflections and the obtained (measured) deflections from FWD tests are closely matched to each other within a tolerable limit. However, this process is substantially time-consuming and poses some difficulties due to inherent inaccuracies in the results. In this study, synthetically derived deflections from a typical flexible pavement are used to estimate asphaltic concrete layer’s elastic modulus, Poisson’s ratio and thickness. Furthermore, artificial neural network (ANN) is utilized to determine the structural parameters, and it can be clearly seen that satisfactory results are obtained. ANN estimation of the three pavement layer characteristic parameters, that is, layer elastic modulus, Poisson’s ratio and layer thickness, was carried out for the first time in the study.     

Advances in backcalculating the mechanical properties of flexible pavements

In current practice, the evaluation of the performance of existing road pavements has become a priority issue for many highway engineers. To make appropriate rehabilitation and management decisions the engineer must rely on an efficient method for determining the structural conditions of pavements. Nondestructive testing (NDT) reveals the stress–strain properties of pavement layers at relatively low strain levels. Since the theoretical approaches used to determine the stress–strain relationships in pavement layers calculate the deflections for given mechanical properties, it is necessary to make an inversion using a backcalculation tool. Several methods have been developed to backcalculate the mechanical properties of flexible pavement; these methods vary in analysis type, material model, and optimization algorithm. This study is designed to explain these methods and to compare and contrast them in terms of modeling precision, computational expense, and calculation details. Consequently, innovations and advances in backcalculating flexible pavements are considered in this paper.     

Analysis of learning rate and momentum term in backpropagation neural network algorithm trained to predict pavement performance

Pavement performance modeling is a critical component of any pavement management system (PMS) decision-making process. A characteristic feature of pavement performance models is that they are formulated and estimated statistically from field data. The statistical modeling can only consider no more than a few of the parameters, in a simplified manner, and in some cases various transformations of the original data. Lately, artificial neural networks (ANNs) were applied to pavement performance modeling. The ANNs offer a number of advantages over the traditional statistical methods, caused by their generalization, massive parallelism and ability to offer real time solutions. Unfortunately, in pavement performance modeling, only simulated data were used in ANNs environment. In this paper, real pavement condition and traffic data and specific architecture are used to investigate the effect of learning rate and momentum term on back-propagation algorithm neural network trained to predict flexible pavement performance. On the basis of the analysis it is concluded that an extremely low learning rate around 0.001–0.005 combination and momentum term between 0.5–0.9 do not give satisfactory results for the specific data set and the architecture used. It is also established that the learning rate and momentum term, and validation data can be used to identify when over-learning is taking place in a training set.     

Finite element based hybrid evolutionary optimization approach to solving rigid pavement inversion problem

This paper focuses on the development of a new backcalculation method for concrete road structures based on a hybrid evolutionary global optimization algorithm, namely shuffled complex evolution (SCE). Evolutionary optimization algorithms are ideally suited for intrinsically multi-modal, non-convex, and discontinuous real-world problems such as pavement backcalculation because of their ability to explore very large and complex search spaces and locate the globally optimal solution using a parallel search mechanism as opposed to a point-by-point search mechanism employed by traditional optimization algorithms. SCE, a type of evolutionary optimization algorithms based on the tradeoff of exploration and exploitation, has proved to be an efficient method for many global optimization problems and in some cases it does not suffer the difficulties encountered by other evolutionary computation techniques. The SCE optimization approach is hybridized with a neural networks surrogate finite-element based forward pavement response model to enable rapid computation of global or near-global pavement layer moduli solutions. The proposed rigid pavement backcalculation model is evaluated using field non-destructive test data acquired from a full-scale airport pavement test facility.     

Modeling and analysis of touch on flexible ultra-thin touch sensor panels for AMOLED displays employing finite element methods

The work employs the finite element method (FEM) to model the touch on the flexible ultra-thin touch sensor panel for analyzing touch characteristics and signals. Touch sensor panel readout circuits typically depend on touch signals to determine whether the touch sensor panel is touched or not. However, the ultra-thin touch sensor panel encountered a problem which cannot correctly recognize touch points on this type of touch sensor panel (TSP) on active-matrix organic light emitting diodes (AMOLED) displays since its electrical characteristics are different from the one of the conventional TSP. The modeling techniques for the flexible ultra-thin touch sensor panel on an AMOLED display is used to analyze touch signals from the influence of the thickness of top over layer of the flexible ultra-thin TSP and to observe the variations of mutual capacitance from touch on the flexible ultra-thin TSP. When the flexible ultra-thin touch sensor panel with the thickness of the top over layer less than the threshold thickness of the top over layer is on multi-touch, the phenomenon of the ghost points are generated. The simulation to find the threshold thickness of the top over layer based on the FEM model is conducted, and the simulation results show the top layer thickness should be larger than 107 µm to eliminate the ghost points. Furthermore, a new solution that is an optimization of the electrode pattern of transmitters and receivers in the ultra-thin touch sensor panel to further minimize the threshold thickness of the top over layer of TSP without changing the physical structure of TSP is proposed. The results conducted by using this proposed solution show that TSP top over layer threshold thickness can be reduced to 65 µm without appearance of the ghost points.

     

On-chip actuation of an in-plane compliant bistable micromechanism

A compliant bistable micromechanism has been developed which can be switched in either direction using on-chip thermal actuation. The energy storage and bistable behavior of the mechanism is achieved through the elastic deflection of compliant segments. The Pseudo-Rigid-Body Model was used for the compliant mechanism design, and for analysis of the large deflection flexible segments. To achieve on-chip actuation, the mechanism design was optimized to allow it to be switched using linear motion thermal actuators. The modeling theory and analysis are presented for three design iterations, with two iterations fabricated in the MUMP's process and the third in the SUMMiT process.     

Simulation process of flexible multibody systems with non-modal model order reduction techniques

One important issue for the simulation of flexible multibody systems is the reduction of the flexible body’s degrees of freedom. In this work, nonmodal model reduction techniques for flexible multibody systems within the floating frame of reference framework are considered. While traditionally in the multibody community modal techniques in many different forms are used, here other methods from system dynamics and mathematics are in the focus. For the reduction process, finite element data and user inputs are necessary. Prior to the reduction process, the user first needs to choose boundary conditions fitting the chosen reference frame before defining the appropriate in- and outputs. In this work, four different possibilities of modeling appropriate interface points to reduce the number of inputs and outputs are presented.     

Design and evaluation of visualization support to facilitate decision trees classification

The loosely coupled relationships between visualization and analytical data mining (DM) techniques represent the majority of the current state of art in visual data mining; DM modeling is typically an automatic process with very limited forms of guidance from users. A conceptual model of the visualization support to DM modeling process and a novel interactive visual decision tree (IVDT) classification process have been proposed in this paper, with the aim of exploring humans’ pattern recognition ability and domain knowledge to facilitate the knowledge discovery process. An IVDT for categorical input attributes has been developed and experimented on 20 subjects to test three hypotheses regarding its potential advantages. The experimental results suggested that, compared to the automatic modeling process as typically applied in current decision tree modeling tools, IVDT process can improve the effectiveness of modeling in terms of producing trees with relatively high classification accuracies and small sizes, enhance users’ understanding of the algorithm, and give them greater satisfaction with the task.     

基于Petri网的工作流过程建模

业务过程建模是整个工作流管理系统的基础,选择一种高效的建模技术对复杂多变的实际业务流程进行形式化表示对构建一个灵活的工作流管理系统起着至关重要的作用。本文利用了Petri网技术给业务过程建模,构造了一个灵活可分析的过程模型：首先介绍了相关的基于Petri网的工作流建模技术,接着描述了Petri网到工作流过程模型执行的映 射,然后给出了一个具体的基于Petri网建模方式的实例,最后利用随机Petri网和概率论的一些知识对该模型进行了时间性能分析。     

基于计算机视觉的高速路面状态检测方法

路面状态检测技术是辅助高速公路监管部门及时发现结冰、积雪等不良路况的重要手段。针对传统基于硬件设备的路面状态检测技术存在成本较高、检测范围受局限等问题,提出了一种基于计算机视觉的高速路面状态检测方法。该方法首先将融合了空间注意力机制和通道注意力机制的Attention模块与具有高分割精度的U-Net网络相结合,对路面区域图像进行分割提取;之后实现了一种基于循环生成对抗网络的路面阴影消除算法,对已经提取的路面图像进行阴影消除;最后基于残差结构构建了路面状态分类器,实现高准确率的路面状态检测。实验结果表明,采用该方法可以消除路面状态检测过程中高速公路两侧景物和路面阴影对状态检测带来的干扰,实现了对路面干燥、积雪、积水和结冰4类状态的准确识别。基于高速公路监控视频进行测试时,识别率可达97.9%。     

Application of ANFIS for modeling of layer thickness of chromium carbonitride coating

In the present work, layer thickness of duplex coating made from thermo-reactive deposition and diffusion has been predicted by Adaptive network-based fuzzy inference systems (ANFIS). A duplex surface treatment on five steels has been developed involving nitrocarburizing and followed by chromium thermo-reactive deposition (TRD) techniques. The TRD process was performed in molten salt bath at 550, 625 and 700 °C for 1–30 h. The process formed a thickness up to 9.5 μm of chromium carbonitride coatings on a hardened diffusion zone. A model based on ANFIS for predicting the layer thickness of duplex coating of the specimens has been presented. To build the model, training and testing using experimental results from 84 specimens were conducted. The data used as inputs in ANFIS models are arranged in a format of twelve parameters that cover the chemical composition (C, Mn, Si, Cr, Mo, V, W), the pre-nitriding time, ferro-chromium particle size, ferro-chromium weight percent, salt bath temperature and coating time. According to these input parameters, in the Adaptive network-based fuzzy inference system models, the layer thickness of duplex coating of each specimen was predicted. The training and testing results in ANFIS models have shown a strong potential for predicting the layer thickness of duplex coating.     

具有一维带限Weierstrass分形特征实际路面电磁散射FDTD研究

一般的实际路面系统是由沥青混凝土面层、水泥碎石联结层、水泥稳定碎石基层和路基层等构成的多层介质,可以看作是具有一维带限Weierstrass分形特征的水泥混凝土路面系统。运用时域有限差分方法(FDTD)研究了这种实际的水泥混凝土路面系统电磁散射,具体计算了3层路面系统电磁散射的双站散射系数,得出了散射系数随散射角和入射波频率变化的曲线。分析了散射系数随路面分维数、入射波频率、入射角、路面材料介电常数、面层厚度、基层厚度等参数变化的规律,讨论了面层存在圆柱形空洞时,空洞内填充物变化对散射系数的影响,得到了具有一维带限Weierstrass分形特征的实际路面系统电磁散射的特性。数值计算结果表明:路面分维数、入射波频率、入射角、路面材料介电常数、面层厚度、基层厚度、面层存在的空洞对散射系数的影响是非常复杂的。     

深水柔性管道铺设过程的动态仿真

针对深水柔性管道铺设的一般过程,将铺设过程离散成若干典型工况,并通过非线性时域有限元法实现铺设过程的动态仿真分析。阐述仿真所涉及的基本方程、模型与基本单元、载荷工况与动态响应统计的具体处理技术。以水深1 000 m柔性管道的铺设为例,着重展示动态仿真技术在铺设设计中的应用。分析实例表明：通过非线性时域动态分析技术对深水柔性管道的铺设过程进行仿真是可行的,可以有效地为铺设设计提供指导。     

A microstructure for in situ determination of residual strain

This work presents a new strain sensor with a compact structure. The strain sensor comprises of a pair of cantilever beams with different lengths connected by a short tip. The residual strain causes two beams to deflect each other, thereby magnifying the deflection, which is measured by the tip. The displacement is independent of both Young's modulus and the film's thickness. An analytical model is derived to relate the measured displacement to residual strain. Finite-element modeling is also used to analyze the model. This work also thoroughly considers other factors that influence the designs and the implicit limitations of the strain sensors. Experimental results with an SiO₂ film as well as undoped LPCVD polysilicon films are used to demonstrate the effectiveness of the proposed structure     

Evaluation of decision trees: a multi-criteria approach

Data mining (DM) techniques are being increasingly used in many modern organizations to retrieve valuable knowledge structures from organizational databases, including data warehouses. An important knowledge structure that can result from data mining activities is the decision tree (DT) that is used for the classification of future events. The induction of the decision tree is done using a supervised knowledge discovery process in which prior knowledge regarding classes in the database is used to guide the discovery. The generation of a DT is a relatively easy task but in order to select the most appropriate DT it is necessary for the DM project team to generate and analyze a significant number of DTs based on multiple performance measures. We propose a multi-criteria decision analysis based process that would empower DM project teams to do thorough experimentation and analysis without being overwhelmed by the task of analyzing a significant number of DTs would offer a positive contribution to the DM process. We also offer some new approaches for measuring some of the performance criteria.     

Nonlinear system identification of large-scale smart pavement systems

This paper proposes a novel model for predicting complex behavior of smart pavements under a variety of environmental conditions. The mathematical model is developed through an adaptive neuro fuzzy inference system (ANFIS). To evaluate the effectiveness of the ANFIS model, the temperature fluctuations at different locations in smart pavement systems equipped with pipe network systems under solar radiations is investigated. To develop the smart pavement ANFIS model, various sets of input and output field experimental data are collected from large-scale experimental test beds. The solar radiation and the inlet water flow are used as input signals for training complex behavior of the smart pavement ANFIS model, while the temperature fluctuation of the smart pavement system is used for the output signal. The trained model is validated using 20 different data sets that are not used for the training process. It is demonstrated from the simulation that the ANFIS identification approach is effective in modeling complex behavior of the pavement–fluid system under a variety of environmental conditions. Comparison with high fidelity data proves the viability of the proposed approach in pavement health monitoring setting, as well as automatic control systems.     

Performance of thin film silicon MEMS on flexible plastic substrates

The fabrication and characterization of thin film silicon MEMS microbridges on flexible polyethylene terephthalate substrates are described. Surface micromachining using an aluminum sacrificial layer and a maximum processing temperature of 110 °C was used for device fabrication. These microbridges are electrostatically actuated and their deflection at resonance and at low frequencies is measured optically. Quasi-DC deflection with a quadratic dependence of the actuation voltage is observed, and resonance frequencies up to 2 MHz and quality factors of around 500 are measured in vacuum. Bending measurements are performed by subjecting these devices to tensile and compressive strain. The low frequency response (bridge deflection as a function of the applied voltage) was measured in air before bending and after every bending step. Under tensile strain, 16.6% of the devices survive the maximum bending with a radius of curvature of 1 cm, equivalent to a tensile strain 1.25%. In contrast, for compressive strain, 50% of the devices survive the bending corresponding to a radius of curvature of −0.5 cm, equivalent to a compressive strain of −2.5%. Thin film silicon microresonators on flexible plastic substrates can withstand more compressive strain than tensile.     

基于服务组合的柔性流程建模

在分析现有柔性流程建模方法的基础上,总结柔性流程建模的实现途径.在面向角色的柔性流程建模方法中采用角色类的划分和角色的动态选取和配置,简化流程的构造.同时提出将Agent技术和Services相结合,设计一种面向角色服务的、封装的、分层的和去耦合的建模系统,并讨论了基于服务组合的柔性流程建模的实现方案.     

Pothole detection in asphalt pavement images

Pavement condition assessment is essential when developing road network maintenance programs. In practice, the data collection process is to a large extent automated. However, pavement distress detection (cracks, potholes, etc.) is mostly performed manually, which is labor-intensive and time-consuming. Existing methods either rely on complete 3D surface reconstruction, which comes along with high equipment and computation costs, or make use of acceleration data, which can only provide preliminary and rough condition surveys. In this paper we present a method for automated pothole detection in asphalt pavement images. In the proposed method an image is first segmented into defect and non-defect regions using histogram shape-based thresholding. Based on the geometric properties of a defect region the potential pothole shape is approximated utilizing morphological thinning and elliptic regression. Subsequently, the texture inside a potential defect shape is extracted and compared with the texture of the surrounding non-defect pavement in order to determine if the region of interest represents an actual pothole. This methodology has been implemented in a MATLAB prototype, trained and tested on 120 pavement images. The results show that this method can detect potholes in asphalt pavement images with reasonable accuracy.