The improvement of transportation systems and technologic equipment leads to changing technical capabilities of this equipment. With the development of technologies, industrial development is also inevitable, resulting in correspondingly increasing need of transportation of HeavyWeight and OverSize (HW/OS) cargo. The application of a systematic approach in HW/OS cargo transportation processes allows reducing costs of delivery of such a cargo several times, which leads to a dramatic change of economic development and investment attraction conditions. Thus creating a system of criteria for the selection and assessment of HW/OS routes, which would allow selecting the most appropriate route of transportation in terms of cost and time, is expedient for this reason. The algorithm for the assessment of HW/OS cargo transportation routes will be drawn up in this article. This algorithm enables an objective evaluation of HW/OS transportation processes comparing different modes of transport, route segments, cargo transportation and cargo handling technology, and it can be practically applied to any territory.
This paper deals with the analysis of the renovation layer quality of continuous casting steel rolls, developed through the submerged arc surfacing method (SAW). The continuous casting roll was analysed via the degradation phenomena which act during the operation. Four kinds of filler materials were used for the renovation of the worn roll. Surfacing was carried out as a three-layer in order to eliminate the need for intermediate layer formation. The quality of weld deposits was evaluated in terms of the structure, hardness and wear resistance of weld deposits at 23°C and 400°C using pin-on-disc wear test. The best properties showed newly developed filler material W8-WLDC8 from the point of view of the hardness, together with wear resistance of the deposited layers in room and elevated temperatures.
The effect of in-service degradation on the deformation behavior of the material of gas mains in soil acid electrolytes has been studied, and it has been shown that depending on the concentration of the corrosive components of the environment, the strain increment can be up to 20-30%. It has been found that in soil acid electrolytes, degraded pipeline steel shows a tendency to sudden strain jumps, which can cause spontaneous depressurization of the pipeline.
The quality, wear and safety of metal structures can be controlled effectively, provided that surface defects, which occur on metal structures, are detected at the right time. Over the past 10 years, researchers have proposed a number of neural network architectures that have shown high efficiency in various areas, including image classification, segmentation and recognition. However, choosing the best architecture for this particular task is often problematic. In order to compare various techniques for detecting defects such as “scratch abrasion”, we created and investigated U-Net-like architectures with encoders such as ResNet, SEResNet, SEResNeXt, DenseNet, InceptionV3, Inception-ResNetV2, MobileNet and EfficientNet. The relationship between training validation metrics and final segmentation test metrics was investigated. The correlation between the loss function, the , , , and validation metrics and test metrics was calculated. Recognition accuracy was analyzed as affected by the optimizer during neural network training. In the context of this problem, neural networks trained using the stochastic gradient descent optimizer with Nesterov momentum were found to have the best generalizing properties. To select the best model during its training on the basis of the validation metrics, the main test metrics of recognition quality (Dice similarity coefficient) were analyzed depending on the validation metrics. The ResNet and DenseNet models were found to achieve the best generalizing properties for our task. The highest recognition accuracy was attained using the U-Net model with a ResNet152 backbone. The results obtained on the test dataset were and .
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.