Data Augmentation of a Corrosion Dataset for Defect Growth Prediction of Pipelines Using Conditional Tabular Generative Adversarial Networks.

Due to corrosion characteristics, there are data scarcity and uneven distribution in corrosion datasets, and collecting high-quality data is time-consuming and sometimes difficult. Therefore, this work introduces a novel data augmentation strategy using a conditional tabular generative adversarial network (CTGAN) for enhancing corrosion datasets of pipelines. Firstly, the corrosion dataset is subjected to data cleaning and variable correlation analysis. The CTGAN is then used to generate external environmental factors as input variables for corrosion growth prediction, and a hybrid model based on machine learning is employed to generate corrosion depth as an output variable. The fake data are merged with the original data to form the synthetic dataset. Finally, the proposed data augmentation strategy is verified by analyzing the synthetic dataset using different visualization methods and evaluation indicators. The results show that the synthetic and original datasets have similar distributions, and the data augmentation strategy can learn the distribution of real corrosion data and sample fake data that are highly similar to the real data. Predictive models trained on the synthetic dataset perform better than predictive models trained using only the original dataset. In comparative tests, the proposed strategy outperformed other data generation methods.

Predicting the medium-temperature thermal stability of impact-strengthened medium-thick plate aluminum alloy using a back propagation artificial neural network.

A normalized medium-thick plate of aluminum alloy (4038) was impact-strengthened using a free-fall method at room temperature (approximately 20 °C). Specimens were then aged at 450 °C, 550 °C and 650 °C for 10, 20, 30 and 40 min respectively. Micro-hardness of each sample was tested. Micro-structure of samples annealed at 650 °C for different durations was characterized. A three-layer back propagation artificial neural network (BPANN) was trained using actual state parameters of the prepared samples. Results reveal that medium-temperature thermal stability of the prepared plate can be predicted through the BPANN model. Deviation of predicted values from the experimental ones is within 6 %, with a prediction accuracy exceeding 94 %. Variation trend of the predicted and the experimental thermal stability is consistent, but the predicted values are all higher than the measurements. Prediction accuracy of BPANN can be improved by increasing convergence rate of the error function. By adding relevant parameters of the micro-structure from samples aged at 650 °C to the input layer, BPANN model further improve its output and approach the real state of samples. The findings of this study can help researchers reduce the number and cost of experiments. The aim of this work was to predict the medium-temperature thermal stability of impact-strengthened normalized medium-thick plate of aluminum alloy annealed at different temperatures, and it also can be used as reference for other similar experiments.

A Machine Learning Method for Predicting Corrosion Weight Gain of Uranium and Uranium Alloys.

As an irreplaceable structural and functional material in strategic equipment, uranium and uranium alloys are generally susceptible to corrosion reactions during service, and predicting corrosion behavior has important research significance. There have been substantial studies conducted on metal corrosion research. Accelerated experiments can shorten the test time, but there are still differences in real corrosion processes. Numerical simulation methods can avoid radioactive experiments, but it is difficult to fully simulate a real corrosion environment. The modeling of real corrosion data using machine learning methods allows for effective corrosion prediction. This research used machine learning methods to study the corrosion of uranium and uranium alloys in air and established a corrosion weight gain prediction model. Eleven classic machine learning algorithms for regression were compared and a ten-fold cross validation method was used to choose the highest accuracy algorithm, which was the extra trees algorithm. Feature selection methods, including the extra trees and Pearson correlation analysis methods, were used to select the most important four factors in corrosion weight gain. As a result, the prediction accuracy of the corrosion weight gain prediction model was 96.8%, which could determine a good prediction of corrosion for uranium and uranium alloys.

SiamMFC: Visual Object Tracking Based on Mainfold Full Convolution Siamese Network.

Visual tracking task is divided into classification and regression tasks, and manifold features are introduced to improve the performance of the tracker. Although the previous anchor-based tracker has achieved superior tracking performance, the anchor-based tracker not only needs to set parameters manually but also ignores the influence of the geometric characteristics of the object on the tracker performance. In this paper, we propose a novel Siamese network framework with ResNet50 as the backbone, which is an anchor-free tracker based on manifold features. The network design is simple and easy to understand, which not only considers the influence of geometric features on the target tracking performance but also reduces the calculation of parameters and improves the target tracking performance. In the experiment, we compared our tracker with the most advanced public benchmarks and obtained a state-of-the-art performance.

Development of Piezoelectric Energy Harvester System through Optimizing Multiple Structural Parameters.

Road power generation technology is of significance for constructing smart roads. With a high electromechanical conversion rate and high bearing capacity, the stack piezoelectric transducer is one of the most used structures in road energy harvesting to convert mechanical energy into electrical energy. To further improve the energy generation efficiency of this type of piezoelectric energy harvester (PEH), this study theoretically and experimentally investigated the influences of connection mode, number of stack layers, ratio of height to cross-sectional area and number of units on the power generation performance. Two types of PEHs were designed and verified using a laboratory accelerated pavement testing system. The findings of this study can guide the structural optimization of PEHs to meet different purposes of sensing or energy harvesting.

Dense-RefineDet for Traffic Sign Detection and Classification.

Detecting and classifying real-life small traffic signs from large input images is difficult due to their occupying fewer pixels relative to larger targets. To address this challenge, we proposed a deep-learning-based model (Dense-RefineDet) that applies a single-shot, object-detection framework (RefineDet) to maintain a suitable accuracy-speed trade-off. We constructed a dense connection-related transfer-connection block to combine high-level feature layers with low-level feature layers to optimize the use of the higher layers to obtain additional contextual information. Additionally, we presented an anchor-design method to provide suitable anchors for detecting small traffic signs. Experiments using the Tsinghua-Tencent 100K dataset demonstrated that Dense-RefineDet achieved competitive accuracy at high-speed detection (0.13 s/frame) of small-, medium-, and large-scale traffic signs (recall: 84.3%, 95.2%, and 92.6%; precision: 83.9%, 95.6%, and 94.0%). Moreover, experiments using the Caltech pedestrian dataset indicated that the miss rate of Dense-RefineDet was 54.03% (pedestrian height > 20 pixels), which outperformed other state-of-the-art methods.

DIFTOS: A Distributed Infrastructure-Free Traffic Optimization System Based on Vehicular Ad Hoc Networks for Urban Environments.

Aiming to alleviate traffic congestion, many congestion avoidance and traffic optimization systems have been proposed recently. However, most of them suffer from three main problems. Firstly scalability: they rely on a centralized server, which has to perform intensive communication and computational tasks. Secondly unpredictability: they use smartphones and other sensors to detect the congested roads and warn upcoming vehicles accordingly. In other words, they are used to solve the problem rather than avoiding it. Lastly, infrastructure dependency: they assume the presence of pre-installed infrastructures such as roadside unit (RSU) or cellular 3G/4G networks. Motivated by the above-mentioned reasons, in this paper, we proposed a fully distributed and infrastructure-less congestion avoidance and traffic optimization system for VANET (Vehicular Ad-hoc Networks) in urban environments named DIFTOS (Distributed Infrastructure-Free Traffic Optimization System), in which the city map is divided into a hierarchy of servers. The vehicles that are located in the busy road intersections play the role of servers, thus DIFTOS does not rely on any centralized server and does not need internet connectivity or RSU or any kind of infrastructure. As far as we know, in the literature of congestion avoidance using VANET, DIFTOS is the first completely infrastructure-free congestion avoidance system. The effectiveness and scalability of DIFTOS have been proved by simulation under different traffic conditions.