Ensemble learning directed classification and regression of hydrocarbon fuels

Liu, Runze; Liu, Yifan; Duan, Jinyu; Hou, Fang; Wang, Li; Zhang, Xiangwen; Li, Guozhu

doi:10.1016/j.fuel.2022.124520

Cited by 9 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, Parakhin constructed a series of N,N -methylene-bridged polynitro hexaazaisowurtzitane molecules and found the specific impulse higher than CL-20 [24]. Recently, Li and co-workers proposed an effective machine learning (ML) method enabling the high-throughput screening of next-generation fuels from the hydrocarbon subset of GDB-13 and further continued the idea with more advanced methods [25][26][27]. These approaches furnished the ways for designing novel fuels and offered some high-performance candidates.…”

Section: Introductionmentioning

confidence: 99%

Accelerating the Design of High-Energy-Density Hydrocarbon Fuels by Learning from the Data

Wen,

Shan,

Lai

et al. 2023

Molecules

View full text Add to dashboard Cite

In the ZINC20 database, with the aid of maximum substructure searches, common substructures were obtained from molecules with high-strain-energy and combustion heat values, and further provided domain knowledge on how to design high-energy-density hydrocarbon (HEDH) fuels. Notably, quadricyclane and syntin could be topologically assembled through these substructures, and the corresponding assembled schemes guided the design of 20 fuel molecules (ZD-1 to ZD-20). The fuel properties of the molecules were evaluated by using group-contribution methods and density functional theory (DFT) calculations, where ZD-6 stood out due to the high volumetric net heat of combustion, high specific impulse, low melting point, and acceptable flash point. Based on the neural network model for evaluating the synthetic complexity (SCScore), the estimated value of ZD-6 was close to that of syntin, indicating that the synthetic complexity of ZD-6 was comparable to that of syntin. This work not only provides ZD-6 as a potential HEDH fuel, but also illustrates the superiority of learning design strategies from the data in increasing the understanding of structure and performance relationships and accelerating the development of novel HEDH fuels.

show abstract

Section: Introductionmentioning

confidence: 99%

Accelerating the Design of High-Energy-Density Hydrocarbon Fuels by Learning from the Data

Wen,

Shan,

Lai

et al. 2023

Molecules

View full text Add to dashboard Cite

show abstract

A survey on imbalanced learning: latest research, applications and future directions

Chen,

Yang,

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

Imbalanced learning constitutes one of the most formidable challenges within data mining and machine learning. Despite continuous research advancement over the past decades, learning from data with an imbalanced class distribution remains a compelling research area. Imbalanced class distributions commonly constrain the practical utility of machine learning and even deep learning models in tangible applications. Numerous recent studies have made substantial progress in the field of imbalanced learning, deepening our understanding of its nature while concurrently unearthing new challenges. Given the field’s rapid evolution, this paper aims to encapsulate the recent breakthroughs in imbalanced learning by providing an in-depth review of extant strategies to confront this issue. Unlike most surveys that primarily address classification tasks in machine learning, we also delve into techniques addressing regression tasks and facets of deep long-tail learning. Furthermore, we explore real-world applications of imbalanced learning, devising a broad spectrum of research applications from management science to engineering, and lastly, discuss newly-emerging issues and challenges necessitating further exploration in the realm of imbalanced learning.

show abstract

Uncovering the generic and alloy-specific governing parameters of deformation-induced martensitic transformation in austenitic steel

Shen,

Mu,

Wang

et al. 2024

J Mater Sci

View full text Add to dashboard Cite

In this work, a hybrid modeling approach, combining machine learning (ML) and computational thermodynamics, has been applied to predict deformation-induced martensitic transformation (DIMT) and explore the generic and alloy-specific parameters governing DIMT in austenitic steels. The DIMT model was established based on the ensemble ML algorithms and a comprehensive set of physical variables. The developed model is highly generalizable as validated on unseen alloys. The generic governing parameters of DIMT are in good agreement with previous studies in the literature. However, the evaluated alloy-specific governing parameters reveal large differences between grades, e.g., 204 series of austenitic stainless steels has a quite balanced correlation between strain, stress, temperature, and DIMT, while the 301 series has much stronger correlation between stress and DIMT. The findings in the current study emphasize the importance that a general DIMT model for steels should include both stress and strain, as well as other governing parameters, since DIMT can be both stress-assisted and strain-induced transformation, and often the effect of applied mechanical driving force and the formation of new nucleation sites interact. Graphical abstract

show abstract

Ensemble learning directed classification and regression of hydrocarbon fuels

Cited by 9 publications

References 42 publications

Accelerating the Design of High-Energy-Density Hydrocarbon Fuels by Learning from the Data

Accelerating the Design of High-Energy-Density Hydrocarbon Fuels by Learning from the Data

A survey on imbalanced learning: latest research, applications and future directions

Uncovering the generic and alloy-specific governing parameters of deformation-induced martensitic transformation in austenitic steel

Contact Info

Product

Resources

About