Search results

Remaining useful life (RUL) prediction for power transformer maintenance is a challenging task on heterogeneous data. Monitoring data of power transformers are not always compatible or in an identical format; therefore, RUL predictions traditionally work separately on different data. Moreover, chemical molecules used in RUL prediction can be transformed into each other under different conditions, thus forming a complete graph with uncertain adjacency matrix (UAM). This study aims to find and evaluate a new model to achieve better results of RUL prediction than the other baselines.

In this work, the authors propose a spatiotemporal complete graph convolutional network (STCGCN) for RUL prediction in two branches, in which daily and hourly features are extracted from correlated heterogeneous data separately. This study provides a thorough evaluation of the proposed model on real-world data and compare the proposed model with state-of-the-art RUL prediction models.

By using the multibranch structure and EucCos similarity aggregation, STCGCN was able to capture the dynamic spatiotemporal patterns on a variety of heterogeneous data and obtain more accurate prediction results, compared to other time series prediction methods.

In this work, the authors propose a novel multibranch structure to compute feature maps from two heterogeneous data sources efficiently and a novel similarity aggregation method to compute the spatial UAM within the complete graph. Compared with traditional time series prediction models, the model pays attention to the spatial relationships in time series data.

The purpose of this paper is to provide a review of recent systematic and comprehensive advancement in electrospun polymer fiber and their composites with shape memory property.

The nanofiber manufacture technique is initially reviewed. Then, the influence of electrospinning parameters and actuation method has been discussed. Finally, the study concludes with a brief review of recent development in potential applications.

Shape memory polymer (SMP) nanofibers are a type of smart materials which can change shape under external stimuli (e.g. temperature, electricity, magnetism, solvent). In general, such SMP nanofibers could be easily fabricated by mature electrospinning technique. The nanofiber morphology is mainly affected by the electrospinning parameters, including applied voltage, tip-to-collector distance, viscosity of solution, humidity and molecular weight. For actuation method, most SMP nanofibers and their composites can change their shapes in response to heat, magnetic field or solvent, while few can be driven by electricity. Compared with the block SMPs, electrospun SMP nanofibers’ mat with porosity and low mechanical property have a wide potential application field including tissue engineering, drug delivery, filtration, catalysis.

This paper provides a detailed review of shape memory nanofibers: fabrication, actuation and potential application, in the near future.

The purpose of this paper is to investigate the optimal geometry parameters in a dimple/protrusion-pin finned channel with high thermal performance.

The BSL turbulence model is used to calculate the flow structure and heat transfer in a dimple/protrusion-pin finned channel. The optimization algorithm is set as Non-dominated Sorting Genetic Algorithm II (NSGA-II). The high Nusselt number and low friction factor are chosen as the optimization objectives. The pin fin diameter, dimple/protrusion diameter, dimple/protrusion location and dimple/protrusion depth are applied as the optimization variables. An in-house code is used to generate the geometry model and mesh. The commercial software Isight is used to perform the optimization process.

The results show that the Nusselt number and friction factor are sensitive to the geometry parameters. In a pin finned channel with a dimple, the Nusselt number is high at the rear part of the dimple, while it is low at the upstream of the dimple. A high dissipative function is found near the pin fin. In the protrusion channel, the Nusselt number is high at the leading edge of the protrusion. In addition, the protrusion induces a high pressure drop compared to the dimpled channel.

The originality of this paper is to optimize the geometry parameters in a pin finned channel with dimple/protrusion. This is good application for the heat transfer enhancement at the trailing side for the gas turbine.

For a better understanding of the preferences and differences of young consumers in emerging wine markets, this study aims to propose a clustering method to segment the super-new generation wine consumers based on their sensitivity to wine brand, origin and price and then conduct user profiles for segmented consumer groups from the perspectives of demographic attributes, eating habits and wine sensory attribute preferences.

We first proposed a consumer clustering perspective based on their sensitivity to wine brand, origin and price and then conducted an adaptive density peak and label propagation layer-by-layer (ADPLP) clustering algorithm to segment consumers, which improved the issues of wrong centers' selection and inaccurate classification of remaining sample points for traditional DPC (DPeak clustering algorithm). Then, we built a consumer profile system from the perspectives of demographic attributes, eating habits and wine sensory attribute preferences for segmented consumer groups.

In this study, 10 typical public datasets and 6 basic test algorithms are used to evaluate the proposed method, and the results showed that the ADPLP algorithm was optimal or suboptimal on 10 datasets with accuracy above 0.78. The average improvement in accuracy over the base DPC algorithm is 0.184. As an outcome of the wine consumer profiles, sensitive consumers prefer wines with medium prices of 100–400 CNY and more personalized brands and origins, while casual consumers are fond of popular brands, popular origins and low prices within 50 CNY. The wine sensory attributes preferred by super-new generation consumers are red, semi-dry, semi-sweet, still, fresh tasting, fruity, floral and low acid.

Young Chinese consumers are the main driver of wine consumption in the future. This paper provides a tool for decision-makers and marketers to identify the preferences of young consumers quickly which is meaningful and helpful for wine marketing.

In this study, the ADPLP algorithm was introduced for the first time. Subsequently, the user profile label system was constructed for segmented consumers to highlight their characteristics and demand partiality from three aspects: demographic characteristics, consumers' eating habits and consumers' preferences for wine attributes. Moreover, the ADPLP algorithm can be considered for user profiles on other alcoholic products.

The selection of purchasing channels by wine consumers indirectly affects buying experience and satisfaction, therefore, it is of great practical significance to study consumers' preference on channel selection. The purpose of this study is to investigate the current state of consumer selection for purchasing channel and the corresponding influencing factors.

A total of 2,976 valid questionnaires were collected by convenience sampling from 34 provinces, municipalities and autonomous regions of China in 2020 via the Internet, yielding a response rate of 82.2%. A categorical statistical approach was used to understand consumer's selection for each channel. Besides, binary logistic regression model was used to analyze the factors affecting consumers' channel selection.

The results show that Chinese wine consumers' main purchasing channels are as follows: supermarket/mall, wine specialty stores, comprehensive e-business flagship stores, comprehensive e-business individual stores, restaurants and short video and live streaming platforms. Estimation results showed that among the 12 influencing factors in 4 categories, consumers' education and some other factors significantly influenced consumers' decision on wine purchasing channels.

Limited by time and experimental conditions, this study did not analyze the trend of wine consumers' purchasing channel selection. Future work would concentrate on multi-year data and conduct longitudinal comparative analysis.

This study innovatively subdivides the currently popular wine sales channels in Chinese market and conducts research related to consumer channel selection. The results of the study can provide reference for wine producers and distributors to update their strategic layout and also help various channels to understand the characteristics of their customer groups for targeted marketing.

Hazard warning schemes provide efficient hazard recognition and promote project safety. Nevertheless, these schemes perform poorly because the warning information is calibrated for individual characters and is not prioritized for the entire system. This study proposes a hazard warning scheme that prioritizes hazard characters from the inspection process based on the inspectors' experience.

First, hazard descriptions were decomposed into their characters, forming a double-layer network. Second, warning schemes based on cascading effects were proposed. Third, character-based warning schemes were simulated for various experiences.

The results show that when a specific hazard is detected, the degree centrality is the most effective parameter for prioritization, and hazard characters should be prioritized based on betweenness centrality for experienced inspectors, whereas degree centrality is preferred for novice inspectors.

The warning scheme theoretically supplements the information-processing theory in construction hazard warnings and provides a practical warning scheme with priority for the development of automated hazard navigation systems.