Search

Your search keyword '"Wei, Hongyu"' showing total 201 results
Start Over Author "Wei, Hongyu" Search Limiters Full Text
201 results on '"Wei, Hongyu"'

10. Machine Learning for Building Energy and Indoor Environment: A Perspective

Author

Liu, Zhijian, Wu, Di, Wei, Hongyu, and Cao, Guoqing

Subjects
Computer Science - Computers and Society, Computer Science - Learning
Abstract

Machine learning is a promising technique for many practical applications. In this perspective, we illustrate the development and application for machine learning. It is indicated that the theories and applications of machine learning method in the field of energy conservation and indoor environment are not mature, due to the difficulty of the determination for model structure with better prediction. In order to significantly contribute to the problems, we utilize the ANN model to predict the indoor culturable fungi concentration, which achieves the better accuracy and convenience. The proposal of hybrid method is further expand the application fields of machine learning method. Further, ANN model based on HTS was successfully applied for the optimization of building energy system. We hope that this novel method could capture more attention from investigators via our introduction and perspective, due to its potential development with accuracy and reliability. However, its feasibility in other fields needs to be promoted further., Comment: Submitted to a Interdisciplinary Journal

Published
2017

15. Early Warning of Systemic Risk in Commodity Markets Based on Transfer Entropy Networks: Evidence from China.

Author

Zhao, Yiran, Gao, Xiangyun, Wei, Hongyu, Sun, Xiaotian, and An, Sufang

Subjects
COMMODITY exchanges, SYSTEMIC risk (Finance), RUSSIAN invasion of Ukraine, 2022-, PRECIOUS metal industries, ENTROPY
Abstract

This study aims to employ a causal network model based on transfer entropy for the early warning of systemic risk in commodity markets. We analyzed the dynamic causal relationships of prices for 25 commodities related to China (including futures and spot prices of energy, industrial metals, precious metals, and agricultural products), validating the effect of the causal network structure among commodity markets on systemic risk. Our research results identified commodities and categories playing significant roles, revealing that industry and precious metal markets possess stronger market information transmission capabilities, with price fluctuations impacting a broader range and with greater force on other commodity markets. Under the influence of different types of crisis events, such as economic crises and the Russia–Ukraine conflict, the causal network structure among commodity markets exhibited distinct characteristics. The results of the effect of external shocks to the causal network structure of commodity markets on the entropy of systemic risk suggest that network structure indicators can warn of systemic risk. This article can assist investors and policymakers in managing systemic risk to avoid unexpected losses. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

23. Experimental study and characterisation of 316L stainless steel parts fabricated with metal fused filament fabrication

Author

Raza, Abbas, Altaf, Khurram, Ahmad, Faiz, Hussain, Ghulam, Alkahtani, Mohammed, and wei, Hongyu

Abstract

The 3D printing process of Fused Deposition Modelling (FDM) can be used for fabricating metal parts without the need of mold. Metal Material Extrusion uses metal-polymer composite filament in the 3D printer to extrude the green part, then a de-binding process for removing the polymer binder, and eventually, the sintering process under high temperatures for making a metallic part. A comprehensive research is conducted in which sintering parameters including heating rate, dwell time, and sintering atmospheres are varied for metal parts mechanical characteristics including tensile strength, ductility, and density. Moreover, sintering atmospheres including vacuum and argon are taken into consideration in this research study. The metal part is known as silver part which has exhibited a high mechanical strength of 540 MPa, a considerable density of 7.57 g/cm3, and a high hardness of 220 HV under a vacuum sintering atmosphere. Whereas the metal parts produced under argon atmosphere have shown comparatively low mechanical strength 424 MPa, density 7.1 g/cm3 and 177 HV. The results are compared with an industrial benchmark process where catalytic de-binding and sintering are used to achieve 500 MPa tensile strength, density 7.83 g/cm3, and 175 HV. Scanning Electron Microscopy reveals that grains are coarsened in a vacuum, and grains appear peeled off along with small pores in the boundaries. The industrial benchmark part has uniform and finer grains.

Published
2024
Full Text
View/download PDF

30. Online Broadband Impedance Identification for Lithium-Ion Batteries Based on a Nonlinear Equivalent Circuit Model

Author

Wei, Hongyu Pan, Xueyuan Wang, Luning Zhang, Rong Wang, Haifeng Dai, and Xuezhe

Subjects
lithium-ion batteries, impedance, equivalent circuit model, nonlinear, recursive least squares algorithm
Abstract

Models play a crucial role in explaining internal processes, estimating states, and managing lithium-ion batteries. Electrochemical models can effectively illustrate the battery’s mechanism; however, their complexity renders them unsuitable for onboard use in electric vehicles. On the other hand, equivalent circuit models (ECMs) utilize a simple set of circuit elements to simulate voltage–current characteristics. This approach is less complex and easier to implement. However, most ECMs do not currently account for the nonlinear impact of operating conditions on battery impedance, making it difficult to obtain accurate wideband impedance characteristics of the battery when used in online applications. This article delves into the intrinsic mechanism of batteries and discusses the influence of nonstationary conditions on impedance. An ECM designed for non-steady state conditions is presented. Online adaptive adjustment of model parameters is achieved using the forgetting factor recursive least squares (FFRLS) algorithm and varied parameters approach (VPA) algorithm. Experimental results demonstrate the impressive performance of the model and parameter identification method, enabling the accurate acquisition of online impedance.

Published
2023
Full Text
View/download PDF

32. Triple Intergenotype Recombination of Human Astrovirus 5, Human Astrovirus 8, and Human Astrovirus 1 in the Open Reading Frame 1a, Open Reading Frame 1b, and Open Reading Frame 2 Regions of the Human Astrovirus Genome

Author

Wei, Hongyu, primary, Kumthip, Kattareeya, additional, Khamrin, Pattara, additional, Yodmeeklin, Arpaporn, additional, Jampanil, Nutthawadee, additional, Phengma, Phitchakorn, additional, Xie, Zhenfeng, additional, Ukarapol, Nuthapong, additional, Ushijima, Hiroshi, additional, and Maneekarn, Niwat, additional

Published
2023
Full Text
View/download PDF

47. Past and present of functionally graded coatings: Advancements and future challenges

Author

Fathi, Reham, Wei, Hongyu, Saleh, Bassiouny, Radhika, N., Jiang, Jinghua, Ma, Aibin, Ahmed, Mahmoud H., Li, Qin, Ostrikov, Kostya Ken, Fathi, Reham, Wei, Hongyu, Saleh, Bassiouny, Radhika, N., Jiang, Jinghua, Ma, Aibin, Ahmed, Mahmoud H., Li, Qin, and Ostrikov, Kostya Ken

Abstract

Advanced engineering applications necessitate developing a new class of surface coatings that protect the surface components in these applications while also meeting the conflicting requirements for the necessary properties to improve the surface performance of many parts in biomedical, aerospace, electronics, automotive, marine, oil and gas pipelines, as well as electronics fields. However, surface coatings on many constituents have remained a difficult task for researchers due to the synchronous requirement for opposing characteristics in the same coating. In recent years, functionally graded coatings (FGCs) have been widely used to protect surfaces through achieving specific characteristics from one location to another to be suitable for different operating conditions. Deposition of FGCs with gradient behavior and high accuracy on the surface of substrate material is a versatile and successful approach for enhancing characteristics of the substrate material, primarily to increase its functionality and life span. Therefore, this review paper presents a detailed analysis of the extensively used production techniques to develop FGCs based on the process state during deposition. Also, the microstructure features, mechanical properties, wear resistance, and corrosion behavior of the produced FGCs have been explored in detail. Furthermore, the current review paper focuses on understanding FGC classifications and applications, as well as research gaps and future directions for these coatings. The findings of this paper are expected to give researchers and designers in this field a variety of options for permanent surfaces protection via following a well-organized review methodology.

Published
2022

48. Effect of raster angle and infill pattern on the in-plane and edgewise flexural properties of fused filament fabricated acrylonitrile–butadiene–styrene

Author

Qayyum, Hamza, Hussain, Ghulam, Sulaiman, Muhammad, Hassan, Malik, Ali, Aaqib, Muhammad, Riaz, Wei, Hongyu, Shehbaz, Tauheed, Aamir, Muhammad, Altaf, Khurram, Qayyum, Hamza, Hussain, Ghulam, Sulaiman, Muhammad, Hassan, Malik, Ali, Aaqib, Muhammad, Riaz, Wei, Hongyu, Shehbaz, Tauheed, Aamir, Muhammad, and Altaf, Khurram

Abstract

Fused Filament Fabrication (FFF) is a popular additive manufacturing process to produce printed polymer components, whereby their strength is highly dependent on the process parameters. The raster angle and infill pattern are two key process parameters and their effects on flexural properties need further research. Therefore, the present study aimed to print test specimens with varying raster angles and infill patterns to learn their influence on the in-plane and edgewise flexural properties of acrylonitrile–butadiene–styrene (ABS) material. The results revealed that the highest in-plane and edgewise flexural moduli were obtained when printing was performed at 0 ° raster angle. In comparison, the lowest values were obtained when the printing was executed with a 90 ° raster angle. Regarding the infill pattern, the tri-hexagon pattern showed the largest in-plane modulus, and the quarter-cubic pattern exhibited the greatest edgewise flexural modulus. However, considering both the modulus and load carrying capacity, the quarter-cubic pattern showed satisfactory performance in both planes. Furthermore, scanning electron microscopy was used to investigate the failure modes, i.e., raster rupture, delamination of successive layers and void formation. The failure occurred either due to one or a combination of these modes.

Published
2022

49. Automated EEG Pathology Detection Based on Significant Feature Extraction and Selection.

Author

Zhong, Yunning, Wei, Hongyu, Chen, Lifei, and Wu, Tao

Subjects
*ELECTROENCEPHALOGRAPHY, *FEATURE selection, *FEATURE extraction, *PATHOLOGY, *RANDOM forest algorithms, *MACHINE learning, *WAKEFULNESS
Abstract

Neurological diseases are a significant health threat, often presenting through abnormalities in electroencephalogram (EEG) signals during seizures. In recent years, machine learning (ML) technologies have been explored as a means of automated EEG pathology diagnosis. However, existing ML-based EEG binary classification methods largely focus on extracting EEG-related features, which may lead to poor performance in classifying EEG signals by overlooking potentially redundant information. In this paper, we propose a novel Kruskal–Wallis (KW) test-based framework for EEG pathology detection. Our framework first divides EEG data into frequency sub-bands using wavelet packet decomposition and then extracts statistical characteristics from each selected coefficient. Next, the piecewise aggregation approximation technique is used to obtain the aggregated feature vectors, followed by the KW statistical test methodology to select significant features. Finally, three ensemble learning classifiers, random forest, categorical boosting (CatBoost), and light gradient boosting machine, are used to classify the extracted significant features into normal or abnormal classes. Our proposed framework achieves an accuracy of 89.13%, F1-score of 87.60%, and G-mean of 88.60%, respectively, outperforming other competing techniques on the same dataset, which shows the great promise in EEG pathology detection. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results