Search

Accurate and fast detection of pavement distress can provide reliable and effective technical support for pavement maintenance and rehabitation. Recently, deep learning has been widely used in pavement distress detection. However, its application is still limited by the laborious and difficult annotation process due to the complex topology of pavement distress. In this study, we propose a pavement anomaly detection network (PAD Net), which is a semi-supervised learning approach based on generative adversarial networks for identifying pixel-level anomalous image segments. We build a mapping function for unpaired abnormal and normal pavement images through a framework containing two generators and three novel discriminators. The framework is capable of maintaining background pixels and modifying anomalous foreground regions with the help of multi-style discriminators that consider interrelationships of multi-scale generated images. Meanwhile, pixel-level abnormal areas are detected through an end-to-end mask channel. Experiments show that our approach is able to achieve 80.75% accuracy on our dataset without pixel-level or patch-level annotations. Quantitative comparisons with several prior semi-supervised methods demonstrate the superiority of our approach.

AbstractTo construct urban metro stations, the concrete diaphragm walls are widely used as the support of deep foundation. During the installation of concrete diaphragm wall, the global instability of slurry trench may occur due to the insufficient internal support. The instability originates at a shallow depth blow ground surface and propagates to the ground surface. This paper develops a three-dimensional mechanism for analysing the trench global instability. In the mechanism, the instability is initiated by the movement of a rigid block with conical discontinuity surfaces. The trench stability is analysed using the kinematic approach of limit analysis and the upper bound solution of the safety factor is obtained. The optimal mechanism is achieved through minimising the safety factor. The critical depth of instability and the influence zone on the ground surface are identified. With the higher frictional angle, the critical failure depth becomes smaller and the volume of the failure zone decreases. The drop of slurry level significantly increases the risk of trench instability especially for cohesionless soils. The mechanism is validated through analysing the slurry trench instability during the construction of a subway station in Suzhou, China. The analysis result shows a close agreement with the field measurements.

This study investigates the potential of ZVI on Cd(II) contaminated soil remediation through laboratory experiment, mechanism study and field application. The results show that the dosage of ZVI, the initial concentration level and the reaction time have significant impacts on Cd(II) adsorption and about 88% of aqueous Cd(II) can be removed from soils. The ZVI is observed to promote the increase of Cd(II) residual fraction in Cd(II) contaminated soils according to the sequential extraction procedure (SEP) results. Regression of the laboratory experimental data based on the Langmuir isotherm equation shows the adsorption capacity can reach 34.7 mg/g. Such a high value is attributed to physical and chemical adsorption, which is proved by X-ray diffraction patterns (XRD), scanning electron microscope images (SEM), and Brunner-Emmet-Teller & Barret–Joyner–Halenda (BET-BJH) analysis. The field application shows that the ZVI can reduce the Cd(II) content in soils and brown rice by 51% and alleviate soil acidification, resulting in a 9.4% increase in rice yields.

Eggplant, the fruit of Solanum melongenaL. (Solanaceae), is applied externally to relieve the symptoms of chilblains in the folk in East Asia. However, the mechanisms and biological ingredients are not clear. A network pharmacology approach was used to shed light on the mechanisms of eggplant against chilblains, which illustrated that anti-inflammation and antioxidation are mainly involved in the curative effects. Bioassay-guided assays led to the isolation of 44 ingredients (1–44), including two new natural compounds (1–2) and 42 known compounds. Thirteen compounds (3–15)were first reported from the Solanumgenus. The anti-inflammatory and antioxidative effects of all isolates were evaluated, and the results showed that 11 compounds have anti-inflammatory activity and 27 have antioxidant activity. Fatty acids, flavonoids, alkaloids, phenolic acids, saponins, and lignans from eggplant have certain anti-inflammatory and antioxidant effects. These results provide a scientific basis for eggplant to treat chilblains.

This paper deals with surface wave propagation (WP) effects on buried segmented pipelines. Both simplified analytical model and finite element (FE) model are developed for estimating the axial joint pullout movement of jointed concrete cylinder pipelines (JCCPs) of which the joints have a brittle tensile failure mode under the surface WP effects. The models account for the effects of peak ground velocity (PGV), WP velocity, predominant period of seismic excitation, shear transfer between soil and pipelines, axial stiffness of pipelines, joint characteristics, and cracking strain of concrete mortar. FE simulation of the JCCP interaction with surface waves recorded during the 1985 Michoacan earthquake results in joint pullout movement, which is consistent with the field observations. The models are expanded to estimate the joint axial pullout movement of cast iron (CI) pipelines of which the joints have a ductile tensile failure mode. Simplified analytical equation and FE model are developed for estimating the joint pullout movement of CI pipelines. The joint pullout movement of the CI pipelines is mainly affected by the variability of the joint tensile capacity and accumulates at local weak joints in the pipeline.