Search

A recurrent neural network (RNN) called CrackNet‐R is proposed in the article for fully automated pixel‐level crack detection on three‐dimensional (3D) asphalt pavement surfaces. In the article, a new recurrent unit, gated recurrent multilayer perceptron (GRMLP), is proposed to recursively update the internal memory of CrackNet‐R. Unlike the widely used long short‐term memory (LSTM) and gated recurrent unit (GRU), GRMLP is intended for deeper abstractions on the inputs and hidden states by conducting multilayer nonlinear transforms at gating units. CrackNet‐R implements a two‐phase sequence processing: sequence generation and sequence modeling. Sequence generation is specifically developed in the study to find the best local paths that are most likely to form crack patterns. Sequence modeling predicts timely probabilities of the input sequence being a crack pattern. In terms of sequence modeling, GRMLP slightly outperforms LSTM and GRU by using only one more nonlinear layer at each gate. In addition to sequence processing, an output layer is proposed to produce pixel probabilities based on timely probabilities predicted for sequences. The proposed output layer is critical for pixel‐perfect accuracy, as it accomplishes the transition from sequence‐level learning to pixel‐level learning. Using 3,000 diverse 3D images, the training of CrackNet‐R is completed through optimizing sequence modeling, sequence generation, and the output layer serially. The experiment using 500 testing pavement images shows that CrackNet‐R can achieve high Precision (88.89%), Recall (95.00%), and F‐measure (91.84%) simultaneously. Compared with the original CrackNet, CrackNet‐R is about four times faster and introduces tangible improvements in detection accuracy. [ABSTRACT FROM AUTHOR]

This study used high-temperature melting experiments, optical microscopy, and scanning electron microscopy to investigate the effects of various Ce contents (0 wt.%~0.0165 wt.%) on the microstructure and TiN precipitation behavior in high-titanium steel during slow cooling solidification. The findings show that the microstructure of the solidified steel in each experiment are equiaxed grains at a cooling rate of 0.17 ℃/s. TiN mainly precipitates in the Liquid + δ two-phase region in this experimental steel. CeAlO3 and Ce2O2S precipitate before TiN, and their small lattice misfit with TiN (7.55% and 7.90%, respectively) are the primary cause of their propensity to act as the cores of TiN heterogeneous nucleation. The TiN area density in each experimental steel increases from 38.6 no./mm2 → 61.4 no./mm2 → 89.3 no./mm2 → 105.8 no./mm2 when the Ce content in the steel rises from 0 wt.% → 0.0015 wt.% → 0.0058 wt.% → 0.0165 wt.%. [ABSTRACT FROM AUTHOR]

Pavement friction and texture characteristics are important aspects of road safety. Despite extensive studies conducted in the past decades, knowledge gaps still remain in understanding the relationship between pavement macrotexture and surface skid resistance. This paper implements discrete wavelet transform to decompose pavement surface macrotexture profile data into multi-scale characteristics and investigate their suitability for pavement friction prediction. Pavement macrotexture and friction data were both collected within the wheel-path from six High Friction Surface Treatment sites in Oklahoma using a high-speed profiler and a Grip Tester. The collected macrotexture profiles are decomposed into multiple wavelengths, and the total and relative energy components are calculated as indicators to represent macrotexture characteristics at various wavelengths. Correlation analysis is performed to examine the contribution of the energy indicators on pavement friction. The macrotexture energy within wavelengths from 0.97 mm to 3.86 mm contributes positively to pavement friction while that within wavelengths from 15.44 mm to 61.77 mm shows negative impacts. Subsequently, pavement friction prediction model is developed using multivariate linear regressive analysis incorporating the macrotexture energy indicators. Comparisons between predicted and monitored friction data demonstrates the robustness of the proposed friction prediction model. [ABSTRACT FROM AUTHOR]

The crude oil is in most cases accompanied with water and natural gas. For this reason, it is important to understand the rheology of the oil emulsion. There are already many works relating to rheology of the oil/water emulsion. However, studies on high-pressure rheology of water/crude oil emulsion in the presence of CH4are rare. In this work, light crude oil with characteristics of high wax content, which is typical in Northwest China, was studied. The rheology of water/crude oil emulsion in the presence of CH4under various conditions were fully studied. The results show that the crude oil emulsion showed obvious characteristics of non-Newtonian fluid at a lower temperature. Before water fraction reached a certain limit, the viscosity increases with the increase of water fraction, when water fraction reaches and exceeds the limit the emulsion viscosity drops with the increase of water fraction. The shear stress–shear rate curves become similar as the increase of temperature, indicating the decreasing effect of temperature on the relation between shear stress and shear rate. When the pressure reaches 8 MPa, the shear stress measured with CH4in the system surpasses that measured without CH4. At higher pressure, CH4shows obvious influence on the rheology. [ABSTRACT FROM PUBLISHER]

Copyright of Canadian Journal of Civil Engineering is the property of Canadian Science Publishing and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)